how to get chatgpt to write an essay with citations

• Helldivers 2
• Dragon’s Dogma 2
• Wuthering Waves
• Genshin Impact
• Counter Strike 2
• Honkai Star Rail
• Lego Fortnite
• Stardew Valley
• NYT Strands
• NYT Connections
• Apple Watch
• Crunchyroll
• Prime Video
• Jujutsu Kaisen
• Demon Slayer
• Chainsaw Man
• Solo Leveling
• Beebom Gadgets

How to Use ChatGPT to Write Essays That Impress

Step 1: Use ChatGPT to Find and Refine Essay Topics

• Log into the service and type the following prompt into ChatGPT:

• As you can see, ChatGPT gave several good ideas for our essay. If you want to refine the idea further, you can ask the chatbot to cut out some parts of the idea and replace them. Or, you can ask for more context in certain parts. Example – “Expand more on topic number 5 and what it means.”

Step 2: Ask ChatGPT to Construct an Outline

• With the same chat open, type out “ Give me an essay outline for <selected topic>. Make sure to keep it structured as I’ll use it to write my essay .” In this case, I will use topic number 2 since it aligns with what I had in mind.

• As you can see above, we now have a structured outline for our essay. We can use this to write our essay or have ChatGPT do that job. Nonetheless, it’s a good starting point. As always, you can have the AI chatbot cut out parts of the outline or specifically add new ones depending on your requirement.

Step 3: Get ChatGPT to Cite Sources for Your Essay

Even though we have the idea and the outline, we will need to do our research for proof supporting our essay. Thankfully, ChatGPT can be of some help here. Since the chatbot is adept at moderate research, users can get a general idea of where to look for gathering information. Let’s begin doing that.

• Let’s begin asking ChatGPT for sources. With the same chat open, type in the following prompt:

• Now we have a list of 10 sources we can reference from. However, you can also see that ChatGPT mentions the year 2021 in some of them. Therefore, it’s best to use these websites but navigate to the latest pages pertaining to your essay for research. This applies to every topic, so always do it. Also, chatbots like ChatGPT have a habit of hallucinating and making up information, so do be careful.

Step 4: Have ChatGPT Write the Essay

• In the same chat, type the following prompt – “With the topic and outline available to you, generate a 700-word essay. Make sure to keep it structured and concise yet informational. Also, keep in mind my target audience is <Insert target audience> so cater to that accordingly.”
• In the middle of the essay, ChatGPT might stop and not answer. Simply type “ Continue ,” and it will finish the rest of the essay.

Step 5: Edit the Essay with ChatGPT

No matter if you have used ChatGPT to draft a complete essay or have written one yourself, you can use this step to make ChatGPT your co-editor and grammar checker. While your essay might need an initial look from a human, you can definitely use the bot to hash out the tone and add little details.

• Either open up the same chat or have your essay already in the clipboard. With that done, type out the following prompt:

Step 6: Export the Essay for Submission

However, for those who want to export the essay into a more aesthetic format, we have just the thing for you. There is no shortage of best ChatGPT Chrome extensions on the internet right now. We have one such selection linked in our list that can export selective chats onto beautiful image formats if you want to show off your essay. Check it out and let us know how you liked it.

Bonus: ChatGPT and AI Apps to Write Essays

1. writesonic.

Ryter is another helpful AI writing assistant that not only helps with essays but all types of articles. The service is powered by a language model that gives it intelligence. Rytr comes with 40+ different use cases and 20+ writing tones for all types of written material. For those who don’t want to stick to English, it even comes with support for 30+ languages.

Upanishad Sharma

Combining his love for Literature and Tech, Upanishad dived into the world of technology journalism with fire. Now he writes about anything and everything while keeping a keen eye on his first love of gaming. Often found chronically walking around the office.

Im student i want to become financially independent woman in life so I want esay essay write

I am housewife and I want easy essay I want to change my life my husband was job less and I want to work online part time job plz help I am enter pass

Add new comment

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

How to make ChatGPT provide sources and citations

One of the biggest complaints about ChatGPT is that it provides information, but the accuracy of that information is uncertain. Those complaints exist because ChatGPT doesn't provide sources, footnotes, or links to where it derived information used in its answers.

Also: 4 things Claude AI can do that ChatGPT can't  

But that's not entirely true -- and ChatGPT can do more.

If you know how to properly prompt ChatGPT, it will give you sources. Here's how.

1. Write a query and ask ChatGPT

To start, you need to ask ChatGPT something that needs sources or citations. I've found it's better to ask a question with a longer answer, so there's more "meat" for ChatGPT to chew on. 

Also: The best AI chatbots: ChatGPT and other interesting alternatives to try

Keep in mind that ChatGPT can't provide any information after 2021 and that requests for information pre-internet (say, for a paper on Ronald Reagan's presidency) will have far fewer available sources.

Here's an example of a prompt I wrote on a topic that I worked on a lot when I was in grad school:

Describe the learning theories of cognitivism, behaviorism, and constructivism

2. Ask ChatGPT to provide sources

This is where a bit of prompt engineering comes in. A good starting point is with this query:

Please provide sources for the previous answer

I've found that this prompt often provides offline sources, books, papers, etc. The problem with offline sources is you can't check their veracity. But it's a starting point. A better query is this:

Please provide URL sources

This prompt specifically tells ChatGPT that you want clickable links to sources. You can also tweak this up by asking for a specific quantity of sources, although your mileage might vary in terms of how many you get back:

Please provide 10 URL sources

In our next step, we'll see what we can do with these.

3. Push ChatGPT to give you higher-quality sources

Remember that ChatGPT (and most large language model AIs) respond well to detail and specificity . So if you're asking for sources, you can push for higher-quality sources. You'll need to clearly specify you need reliable and accurate sources. While this won't necessarily work, it may remind the AI to give you more useful responses. For example:

Please provide me with reputable sources to support my argument on... (whatever the topic is you're looking at)

You can also tell ChatGPT the kinds of sources you want. If you're looking for scholarly articles, peer-reviewed journals, books, or authoritative websites, mention these preferences explicitly. For example:

Please recommend peer-reviewed journals that discuss... (and here, repeat what you discussed earlier in your conversation)

When dealing with abstract concepts or theories, request that ChatGPT provide a conceptual framework along with real-world examples. Here's an example:

Can you describe the principles of Vygotsky's Social Development Theory and provide real-world examples where these principles were applied, including sources for these examples?

This approach not only gives you a theoretical explanation but also practical instances where you can trace back the original sources or case studies.

Another idea is to use sources that don't have link rot (that is, they're no longer online at the URL that ChatGPT might know). Be careful with this, though, because ChatGPT doesn't know of things after 2021. So, while you might be tempted to use a prompt like this:

Please provide me with sources published within the past five years

Instead, consider using a prompt like this:

Please provide sources published from 2019 through 2021.

And, as always, don't assume that whatever ChatGPT gives you is accurate. It's still quite possible it will completely fabricate answers, even to the point of making up the names of what seem like academic journals. It's a fibber . It's a sometimes helpful tool, but also a fibber.

4. Attempt to verify/validate the provided sources

Keep in mind this golden rule about ChatGPT-provided sources: ChatGPT is more often wrong than right .

Across the many times I've asked ChatGPT for URL sources, roughly half are just plain bad links. Another 25% or more are links that go to topics completely or somewhat unrelated to the one you're trying to source. 

Also: How to use ChatGPT: Everything you need to know

For example, I asked for sources on a backgrounder for the phrase "trust but verify", generally popularized by US President Ronald Reagan. I got a lot of sources back, but most didn't actually exist. I got some back that correctly took me to active pages on the Reagan Presidential Library site, but the page topic had nothing to do with the phrase in question.

I had a bit better luck with my learning theory question from step 1. There, I got back offline texts from the people who I knew from my studies who had actually worked on those theories. I also got back URLs, but again, only about two in 10 actually worked or were accurate.

Also: 40% of workers will have to reskill in the next three years due to AI, says IBM study

But don't despair. The idea isn't to expect ChatGPT to provide sources that you can immediately use. If you instead think of ChatGPT as a research assistant, it will give you some great starting places. Use the names of the articles (which may be completely fake or just not accessible) and drop them into Google. That process will give you some interesting search queries, which will more than likely lead to some interesting reads and material that can legitimately go into your research.

Also, keep in mind that you're not limited to using ChatGPT. Just because ChatGPT exists doesn't mean you should forget all the tools available to researchers and students. Do your own web searches. Check with primary sources and subject matter experts if they're available to you. If you're in school, you can even ask your friendly neighborhood librarian for help.

Also:  How to use ChatGPT to create an app

Don't forget that there are many excellent traditional sources. For example, Google Scholar and JSTOR  provide access to a wide range of academically acceptable resources you can cite with reasonable confidence.

One final point: if you merely cut and paste ChatGPT sources into whatever research you're doing, you're likely to get stung. Use it for clues, not as a way to avoid the real work of research.

5. Consider upgrading to ChatGPT Plus

While ChatGPT Plus is more expensive (it's $20/month), it has numerous advantages over the free version. In particular, it uses the GPT-4 model, and it adds support for both Code Interpreter and plugins. For our purposes here, the WebPilot plugin can prove very helpful.

Also: How (and why) to subscribe to ChatGPT Plus

WebPilot gives ChatGPT the ability to search the web. This effectively eliminates the 2021 cutoff point for the ChatGPT knowledge base. It also allows ChatGPT to access the web to find more current sources and citations. This has the advantage of reducing the link rot symptoms that come from using a 2021 database in 2023 and beyond.

Also: GPT-3.5 vs GPT-4: Is ChatGPT Plus worth its subscription fee?

Do be aware, however, that even with current web access, ChatGPT can still hallucinate. In other words, the AI will still make stuff up, including valid-seeming sources that don't exist and have never existed. Continue to double-check everything.

How do you put sources in APA format? 

APA style is a citation style that's often required in academic programs. APA stands for American Psychological Association, and I've often thought that they invented these style rules in order to get more customers. But, seriously, the definitive starting point for APA style is the Purdue OWL . It provides a wide range of style guidelines. 

Also:  How to use ChatGPT to build your resume

Be careful: Online style formatters might not do a complete job, and you may get your work returned by your professor. It pays to do the work yourself -- and use care doing it. 

How can I make ChatGPT provide more reliable sources for its responses?

This is a good question. I have found that sometimes -- sometimes -- if you ask ChatGPT to give you more sources, or re-ask for sources, it will give you new listings. If you tell ChatGPT that the sources it provided were erroneous, it will sometimes give you better ones. It may also just apologize and give excuses. Another approach is to re-ask your original question with a different focus or direction, and then ask for sources for the new answer. 

Also: 5 ways you can use ChatGPT to help you write essays

Once again, my best advice is to avoid treating ChatGPT as a tool that writes for you and more as a writing assistant. Asking for sources, so you can simply cut and paste a ChatGPT response, is pretty much plagiarism. But using ChatGPT's response and any sources you can tease out of it as clues for further research and writing is a completely legitimate way to use this intriguing new tool.

Why are ChatGPT sources often so wrong? 

For some links, it's just link rot. Since all sources are at least three years old, some links may have changed. Other sources are of indeterminate age. Since we don't have a full listing of all of ChatGPT's sources, it's impossible to tell how valid they were to begin with. 

Also: You can build your own AI chatbot with this drag-and-drop tool

But since ChatGPT was trained mostly without human supervision , we know that most of its sources weren't vetted, and so could be wrong, made-up, or completely non-existent.

Trust, but verify.

You can follow my day-to-day project updates on social media. Be sure to follow me on Twitter at @DavidGewirtz , on Facebook at Facebook.com/DavidGewirtz , on Instagram at Instagram.com/DavidGewirtz , and on YouTube at YouTube.com/DavidGewirtzTV .

More on AI tools

How to get chatgpt to browse the web for free, how to save money on internet after the affordable connectivity program sunsets, how to use chatgpt to create an app.

How to Use ChatGPT for Research and Essays

Want to use ChatGPT to help out with research and essays? To avoid inaccurate information, there are certain ways you can use it to your advantage.

For better or worse, OpenAI’s ChatGPT has become a big part of our lives. It’s become integral to gathering information, researching topics, and creating written works. And frankly, not using it might put you at a disadvantage academically.

However, this AI is not flawless; there is a method to use it to help with your essays and research. Using it the right way will help you avoid plagiarism issues or inaccurate information. Here, we’ll show you how to use ChatGPT to write an essay ethically, so it comes out as a quality, factual, and original piece.

1. Draw Your Outline Without ChatGPT

Assuming you already have an idea for your project, the first thing you should do before you hop on ChatGPT’s website is to prepare your thesis and outline without using AI. It’s a vital step to making sure the core of your essay actually comes from you.

If you use ChatGPT to prompt an outline for you, it could promote idea laziness, and you will find ChatGPT’s suggestions may have replaced the ones you could have produced on your own. So, get a piece of paper or a blank word processor page and create an outline for your essay.

Also, ChatGPT will avoid controversial topics—even in an outline. Therefore, you might find yourself with an outline missing vital pieces of historical sections if you rely on it. This bias is one of the major problems with OpenAI’s ChatGPT .

2. Prompt ChatGPT to Draw a Parallel Outline

Before you begin this section, if this is your first time using ChatGPT, you should read our guide on how to use ChatGPT . It will help you with creating an account and defining its capabilities. Once that’s out of the way, you can move on to the next step.

Now that you have an original outline, it doesn’t matter how basic it looks; you can use ChatGPT to create another outline. Craft a prompt with this template:

ChatGPT’s result is far more detailed than our outline. Here, you should adopt the parts of ChatGPT’s outline you would like to integrate into your own. Combine the best of the two and flesh out an outline that will guide you best as you write.

3. Create a ChatGPT Prompt for Each Section

Now that you have an outline with sections, you can begin to hack away at it section by section. Start with your introduction, where you will include your thesis statement. Ask ChatGPT to create multiple thesis statements on your idea, and choose the one that best encapsulates the major point you’re trying to communicate in your essay.

You can do something similar for all the other sections as well. Tell the AI to generate written pieces on your section topics. Don’t forget to add that it communicates the point in the tone you want. In most cases, essays should sound academic. Therefore, our prompt for each section looked like this:

Do not just copy and paste the information it generates; the next step is a vital second part of this methodology.

4. Confirm the Information With a Reputable Source

As you begin to write, you must check if the information you’re getting from ChatGPT is indeed correct. You must do this because ChatGPT occasionally hallucinates , coming up with its own facts and making up sources when you ask it to direct you to where it got its information. In some cases, it blatantly refuses to tell you at all where it got its data.

The free version of ChatGPT is not actively connected to the internet and cannot fetch information after September 2021. If you need this functionality, then it could be time to upgrade to ChatGPT Plus —especially if this is a tool you will be using heavily for work or school.

The bottom line is that you should use a reputable source (such as a book from an authority or an official website) to support every important statement you put down. You can also learn how to use Google to fact-check information .

5. Use ChatGPT for Examples and Breakdowns

It’s counterproductive to write about ideas that you don’t even understand yourself. When you reach a part of your essay that you don’t properly understand, you should go to ChatGPT and have it broken down for you.

That’s really the one thing you can count on ChatGPT to do in this process. It has good skill in crafting useful examples and explaining complicated ideas in a form you can easily understand. A popular way of phrasing a prompt to make ChatGPT explain something complicated is adding “explain like I’m five” to your prompt.

Here we used ChatGPT to break down hip and elbow dysplasia conditions in a way that is easier to understand. And it used analogies like jigsaw puzzles to paint a clearer image of what it might look like.

6. Write the Essay Yourself

As we’ve stated earlier, under no condition should you ask ChatGPT to write your whole essay for you. Not only is that lazy and deceitful, but it could also open you up to plagiarism and submitting incorrect information.

Ensure that every line in your essay is typed with your hands. Besides, if you’re writing an academic essay where you must cite sources, you will still need to corroborate all the points you’ve made with a corresponding authority. That means you’ll have to go and fact-check everything ChatGPT has written and find a corroborating source.

This could even take more time than just writing it yourself because the AI could have hallucinated some of its facts, leading you on a wild goose chase as you try to find a citation for something that doesn’t exist.

Lastly, ChatGPT doesn’t match the nuanced knowledge of a human professional in heavily specialized fields or journals that need up-to-date information. Reading a book or article by an expert, internalizing it, and writing it in your own words will give you far better results than relying on ChatGPT.

7. Polish the Style and Citation With ChatGPT

After writing, you can paste portions of your essay and ask ChatGPT to shorten, lengthen, or optimize the style. ChatGPT is good at mimicking popular styles, and you can use that to your advantage. If you want your writing to sound a little more professional, it can help rephrase it.

If you’re having trouble with citation styles and how to integrate them into your essay, you can present your essay to ChatGPT, give it your sources, and ask it to weld them together for you.

ChatGPT Is a Tool, Not a Solution

You can’t “ChatGPT” away academic or professional work; you must use it the same way you would use a tool. Take a calculator, for instance; it doesn’t replace the mathematician but improves the mathematician. You should use ChatGPT the same way a mathematician will use a calculator: for the boring, repetitive, rote work.

Let the ideas and story come from you and your experiences. And if you want to keep using ChatGPT as a student, make sure you know what you shouldn't do.

Celebrating 150 years of Harvard Summer School. Learn about our history.

Should I Use ChatGPT to Write My Essays?

Everything high school and college students need to know about using — and not using — ChatGPT for writing essays.

Jessica A. Kent

ChatGPT is one of the most buzzworthy technologies today.

In addition to other generative artificial intelligence (AI) models, it is expected to change the world. In academia, students and professors are preparing for the ways that ChatGPT will shape education, and especially how it will impact a fundamental element of any course: the academic essay.

Students can use ChatGPT to generate full essays based on a few simple prompts. But can AI actually produce high quality work, or is the technology just not there yet to deliver on its promise? Students may also be asking themselves if they should use AI to write their essays for them and what they might be losing out on if they did.

AI is here to stay, and it can either be a help or a hindrance depending on how you use it. Read on to become better informed about what ChatGPT can and can’t do, how to use it responsibly to support your academic assignments, and the benefits of writing your own essays.

What is Generative AI?

Artificial intelligence isn’t a twenty-first century invention. Beginning in the 1950s, data scientists started programming computers to solve problems and understand spoken language. AI’s capabilities grew as computer speeds increased and today we use AI for data analysis, finding patterns, and providing insights on the data it collects.

But why the sudden popularity in recent applications like ChatGPT? This new generation of AI goes further than just data analysis. Instead, generative AI creates new content. It does this by analyzing large amounts of data — GPT-3 was trained on 45 terabytes of data, or a quarter of the Library of Congress — and then generating new content based on the patterns it sees in the original data.

It’s like the predictive text feature on your phone; as you start typing a new message, predictive text makes suggestions of what should come next based on data from past conversations. Similarly, ChatGPT creates new text based on past data. With the right prompts, ChatGPT can write marketing content, code, business forecasts, and even entire academic essays on any subject within seconds.

But is generative AI as revolutionary as people think it is, or is it lacking in real intelligence?

The Drawbacks of Generative AI

It seems simple. You’ve been assigned an essay to write for class. You go to ChatGPT and ask it to write a five-paragraph academic essay on the topic you’ve been assigned. You wait a few seconds and it generates the essay for you!

But ChatGPT is still in its early stages of development, and that essay is likely not as accurate or well-written as you’d expect it to be. Be aware of the drawbacks of having ChatGPT complete your assignments.

It’s not intelligence, it’s statistics

One of the misconceptions about AI is that it has a degree of human intelligence. However, its intelligence is actually statistical analysis, as it can only generate “original” content based on the patterns it sees in already existing data and work.

It “hallucinates”

Generative AI models often provide false information — so much so that there’s a term for it: “AI hallucination.” OpenAI even has a warning on its home screen , saying that “ChatGPT may produce inaccurate information about people, places, or facts.” This may be due to gaps in its data, or because it lacks the ability to verify what it’s generating. 

It doesn’t do research  

If you ask ChatGPT to find and cite sources for you, it will do so, but they could be inaccurate or even made up.

This is because AI doesn’t know how to look for relevant research that can be applied to your thesis. Instead, it generates content based on past content, so if a number of papers cite certain sources, it will generate new content that sounds like it’s a credible source — except it likely may not be.

There are data privacy concerns

When you input your data into a public generative AI model like ChatGPT, where does that data go and who has access to it? 

Prompting ChatGPT with original research should be a cause for concern — especially if you’re inputting study participants’ personal information into the third-party, public application. 

JPMorgan has restricted use of ChatGPT due to privacy concerns, Italy temporarily blocked ChatGPT in March 2023 after a data breach, and Security Intelligence advises that “if [a user’s] notes include sensitive data … it enters the chatbot library. The user no longer has control over the information.”

It is important to be aware of these issues and take steps to ensure that you’re using the technology responsibly and ethically. 

It skirts the plagiarism issue

AI creates content by drawing on a large library of information that’s already been created, but is it plagiarizing? Could there be instances where ChatGPT “borrows” from previous work and places it into your work without citing it? Schools and universities today are wrestling with this question of what’s plagiarism and what’s not when it comes to AI-generated work.

To demonstrate this, one Elon University professor gave his class an assignment: Ask ChatGPT to write an essay for you, and then grade it yourself. 

“Many students expressed shock and dismay upon learning the AI could fabricate bogus information,” he writes, adding that he expected some essays to contain errors, but all of them did. 

His students were disappointed that “major tech companies had pushed out AI technology without ensuring that the general population understands its drawbacks” and were concerned about how many embraced such a flawed tool.

Explore Our High School Programs

How to Use AI as a Tool to Support Your Work

As more students are discovering, generative AI models like ChatGPT just aren’t as advanced or intelligent as they may believe. While AI may be a poor option for writing your essay, it can be a great tool to support your work.

Generate ideas for essays

Have ChatGPT help you come up with ideas for essays. For example, input specific prompts, such as, “Please give me five ideas for essays I can write on topics related to WWII,” or “Please give me five ideas for essays I can write comparing characters in twentieth century novels.” Then, use what it provides as a starting point for your original research.

Generate outlines

You can also use ChatGPT to help you create an outline for an essay. Ask it, “Can you create an outline for a five paragraph essay based on the following topic” and it will create an outline with an introduction, body paragraphs, conclusion, and a suggested thesis statement. Then, you can expand upon the outline with your own research and original thought.

Generate titles for your essays

Titles should draw a reader into your essay, yet they’re often hard to get right. Have ChatGPT help you by prompting it with, “Can you suggest five titles that would be good for a college essay about [topic]?”

The Benefits of Writing Your Essays Yourself

Asking a robot to write your essays for you may seem like an easy way to get ahead in your studies or save some time on assignments. But, outsourcing your work to ChatGPT can negatively impact not just your grades, but your ability to communicate and think critically as well. It’s always the best approach to write your essays yourself.

Create your own ideas

Writing an essay yourself means that you’re developing your own thoughts, opinions, and questions about the subject matter, then testing, proving, and defending those thoughts. 

When you complete school and start your career, projects aren’t simply about getting a good grade or checking a box, but can instead affect the company you’re working for — or even impact society. Being able to think for yourself is necessary to create change and not just cross work off your to-do list.

Building a foundation of original thinking and ideas now will help you carve your unique career path in the future.

Develop your critical thinking and analysis skills

In order to test or examine your opinions or questions about a subject matter, you need to analyze a problem or text, and then use your critical thinking skills to determine the argument you want to make to support your thesis. Critical thinking and analysis skills aren’t just necessary in school — they’re skills you’ll apply throughout your career and your life.

Improve your research skills

Writing your own essays will train you in how to conduct research, including where to find sources, how to determine if they’re credible, and their relevance in supporting or refuting your argument. Knowing how to do research is another key skill required throughout a wide variety of professional fields.

Learn to be a great communicator

Writing an essay involves communicating an idea clearly to your audience, structuring an argument that a reader can follow, and making a conclusion that challenges them to think differently about a subject. Effective and clear communication is necessary in every industry.

Be impacted by what you’re learning about : 

Engaging with the topic, conducting your own research, and developing original arguments allows you to really learn about a subject you may not have encountered before. Maybe a simple essay assignment around a work of literature, historical time period, or scientific study will spark a passion that can lead you to a new major or career.

Resources to Improve Your Essay Writing Skills

While there are many rewards to writing your essays yourself, the act of writing an essay can still be challenging, and the process may come easier for some students than others. But essay writing is a skill that you can hone, and students at Harvard Summer School have access to a number of on-campus and online resources to assist them.

Students can start with the Harvard Summer School Writing Center , where writing tutors can offer you help and guidance on any writing assignment in one-on-one meetings. Tutors can help you strengthen your argument, clarify your ideas, improve the essay’s structure, and lead you through revisions. 

The Harvard libraries are a great place to conduct your research, and its librarians can help you define your essay topic, plan and execute a research strategy, and locate sources. 

Finally, review the “ The Harvard Guide to Using Sources ,” which can guide you on what to cite in your essay and how to do it. Be sure to review the “Tips For Avoiding Plagiarism” on the “ Resources to Support Academic Integrity ” webpage as well to help ensure your success.

Sign up to our mailing list to learn more about Harvard Summer School

The Future of AI in the Classroom

ChatGPT and other generative AI models are here to stay, so it’s worthwhile to learn how you can leverage the technology responsibly and wisely so that it can be a tool to support your academic pursuits. However, nothing can replace the experience and achievement gained from communicating your own ideas and research in your own academic essays.

About the Author

Jessica A. Kent is a freelance writer based in Boston, Mass. and a Harvard Extension School alum. Her digital marketing content has been featured on Fast Company, Forbes, Nasdaq, and other industry websites; her essays and short stories have been featured in North American Review, Emerson Review, Writer’s Bone, and others.

5 Key Qualities of Students Who Succeed at Harvard Summer School (and in College!)

This guide outlines the kinds of students who thrive at Harvard Summer School and what the programs offer in return.

Harvard Division of Continuing Education

The Division of Continuing Education (DCE) at Harvard University is dedicated to bringing rigorous academics and innovative teaching capabilities to those seeking to improve their lives through education. We make Harvard education accessible to lifelong learners from high school to retirement.

• PRO Courses Guides New Tech Help Pro Expert Videos About wikiHow Pro Upgrade Sign In
• EDIT Edit this Article
• EXPLORE Tech Help Pro About Us Random Article Quizzes Request a New Article Community Dashboard This Or That Game Popular Categories Arts and Entertainment Artwork Books Movies Computers and Electronics Computers Phone Skills Technology Hacks Health Men's Health Mental Health Women's Health Relationships Dating Love Relationship Issues Hobbies and Crafts Crafts Drawing Games Education & Communication Communication Skills Personal Development Studying Personal Care and Style Fashion Hair Care Personal Hygiene Youth Personal Care School Stuff Dating All Categories Arts and Entertainment Finance and Business Home and Garden Relationship Quizzes Cars & Other Vehicles Food and Entertaining Personal Care and Style Sports and Fitness Computers and Electronics Health Pets and Animals Travel Education & Communication Hobbies and Crafts Philosophy and Religion Work World Family Life Holidays and Traditions Relationships Youth
• Browse Articles
• Learn Something New
• Quizzes Hot
• This Or That Game
• Train Your Brain
• Explore More
• Support wikiHow
• About wikiHow
• Log in / Sign up
• Education and Communications
• College University and Postgraduate
• Academic Writing

The Definitive Guide to Citing ChatGPT as a Source

Last Updated: August 5, 2023 Fact Checked

Can you cite ChatGPT?

Apa citations, mla citations, chicago citations.

This article was co-authored by wikiHow staff writer, Nicole Levine, MFA . Nicole Levine is a Technology Writer and Editor for wikiHow. She has more than 20 years of experience creating technical documentation and leading support teams at major web hosting and software companies. Nicole also holds an MFA in Creative Writing from Portland State University and teaches composition, fiction-writing, and zine-making at various institutions. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 7,279 times. Learn more...

When you use ChatGPT or another generative AI tool in your research, you'll need to cite the tool. Because generative AI is so new, the major style guides are still developing their citation requirements. This wikiHow article will teach you how to cite ChatGPT in your research, essay, paper, or other work according to the APA, MLA, and Chicago style guides.

Things You Should Know

• The major style guides are still developing their citation standards for generative AI tools.
• Because ChatGPT's responses are not technically "retrievable," citing ChatGPT is different than citing other electronic sources.
• In Chicago style, you don't have to cite ChatGPT as a source—just mention that you used it in your text.

• Before using ChatGPT in your research, make sure you understand your school, organization, or publisher's stance on AI use .
• Don't use ChatGPT to write your paper and then try to cite it. Only cite ChatGPT when you use the tool to aid in research.

• Now that you can create public links for ChatGPT responses, there's a chance that these links may be required by style guides as retrievable sources. [1] X Research source For now, only MLA has suggested using direct links to ChatGPT responses in citations. Other style guides may follow suit in the future.

• If you used ChatGPT or another AI tool in your research, describe how you used it in your Method section. [3] X Research source
• If citing ChatGPT in another type of essay, response paper, or literature review, you can describe how you used AI in your introduction.
• Consider including the full text of ChatGPT's response in your appendix or other supplemental section.

• OpenAI. (2023). ChatGPT (June 26 version) [Large language model]. https://chat.openai.com/chat

• Parenthetical citations: (OpenAI, 2023)
• Narrative citations: OpenAI (2023)
• When prompted with "Why isn't Pluto a planet?" the ChatGPT generated text indicated that Pluto does not meet the criteria required by the IAU, as it "shares its orbit with a number of other small icy bodies in the Kuiper Belt, a region of the solar system beyond Neptune that contains many similar objects" (OpenAI, 2023).

• When citing ChatGPT in an MLA paper, you'll include the prompt on your Works Cited page, and an abbreviated version of the prompt in your in-text citations.
• While ChatGPT doesn't have the ability to reliably provide its own citations, Bing Chat does . The MLA Style Center recommends using AI tools that provide sources so you can review them, and then cite the original sources in your paper. [4] X Research source

• Initial prompt: "How is masculinity portrayed in the book The Great Gatsby by F. Scott Fitzgerald" prompt. ChatGPT , 13 Feb. version, OpenAI, 26 Jun. 2023, chat.openai.com/chat.
• Follow-up prompts: "In 200 words, describe how Jordan Baker subverted gender roles in The Great Gatsby" follow-up prompt. ChatGPT , 13 Feb. version, OpenAI, 26 Jun. 2023, chat.openai.com/chat.
• While the MLA Style Center has not updated their documentation since ChatGPT began offering direct links to responses, they do state that, when possible, it's best to include a link to the conversation with ChatGPT. [5] X Research source To generate a link, click Copy Link , then replace the URL in your reference with the one you've generated.

• The male characters often express unrelenting desires for control and dominance in their relationships, particularly with women ("How is masculinity portrayed").
• When asked to describe how Jordan Baker subverted gender roles in The Great Gatsby, ChatGPT stated that her athletic abilities "challenge the notion that women should be confined to domestic roles or be dependent on men for their success ("In 200 Words").

• If the prompt is included in the text: 1. Text generated by ChatGPT, March 7, 2023, OpenAI, https://chat.openai.com/chat.
• If the prompt is not included in the text: 1. ChatGPT, response to “How deep is the deepest point in the Atlantic Ocean,” June 26, 2023, OpenAI.

• Alternatively, if you're using author-date citations instead of footnotes and endnotes, you can simply use (ChatGPT, June 26, 2023) instead. Still, you should not add ChatGPT to your bibliography.

Expert Q&A

You might also like.

• ↑ https://help.openai.com/en/articles/7925741-chatgpt-shared-links-faq
• ↑ https://guelphhumber.libguides.com/c.php?g=716556&p=5279441
• ↑ https://apastyle.apa.org/blog/how-to-cite-chatgpt
• ↑ https://style.mla.org/citing-generative-ai
• ↑ https://www.chicagomanualofstyle.org/qanda/data/faq/topics/Documentation/faq0422.html

About This Article

• Send fan mail to authors

Did this article help you?

Featured Articles

Trending Articles

Watch Articles

• Terms of Use
• Privacy Policy
• Do Not Sell or Share My Info
• Not Selling Info

Get all the best how-tos!

Sign up for wikiHow's weekly email newsletter

How To Cite ChatGPT: APA, MLA, Chicago, Harvard

Writing an essay? Need to cite ChatGPT ?

This is the place to be in. Over here, we’re teaching you just that.

We’ll go over a few reference styles:

Citing ChatGPT as a source is 100% free and easy.

Relevant read: How to write an essay with ChatGPT

Let’s learn how to cite ChatGPT and other AI first.

How to cite ChatGPT as a reference

To cite ChatGPT as a reference: List “OpenAI” as the author, include the date of accessing, write “Conversation with ChatGPT” as the title, and insert a URL to ChatGPT.

• You can simply include “chat.openai.com” as the URL.
• Only you can access the conversation.
• However, you can learn how to share the ChatGPT conversation
• Then, you can insert the specific URL as a reference.

Let’s go to the different formats to cite ChatGPT.

• Author : List “OpenAI” as the author.
• Date : Include the date you accessed the chat.
• Title : Use “Conversation with ChatGPT” as the title.
• URL : If applicable, use the URL of the chat interface.

Format : OpenAI. (Year, Month Day). Conversation with ChatGPT. URL

Example: OpenAI. (2023, October 22). Conversation with ChatGPT. chat.openai.com

• Author : Write “OpenAI” as the author.
• Title : Say “Conversation with ChatGPT.”
• Date : Use the date you talked to ChatGPT.
• Medium : State “Web.”

Format : OpenAI. “Conversation with ChatGPT”. Web, Day Month Year. URL

Example: OpenAI. “Conversation with ChatGPT.” Web, 22 October 2023.

• Author : Use “OpenAI” as the author.
• Title : Go with “Conversation with ChatGPT.”
• Date : Note down the date you accessed the chat.
• URL : Include the URL if available.

In this picture, we’re using Notion.so for the essay.

Format : OpenAI. Year. “Conversation with ChatGPT.” Accessed Month Day. URL.

Example: OpenAI. 2023. “Conversation with ChatGPT”. Accessed October 22. chat.openai.com

• Author : State “OpenAI” as the author.
• Year : Use the year you accessed the chat.
• Title : Opt for “Conversation with ChatGPT.”
• URL : Insert the URL if applicable.
• Date Accessed : Include the full date you accessed the chat.

Format : OpenAI (Year) ‘Conversation with ChatGPT’, Available at: URL (Accessed: Day Month Year).

Example: OpenAI (2023) ‘Conversation with ChatGPT’, Available at: chat.openai.com (Accessed: 22 October 2023).

These are the 4 main ways to reference ChatGPT in your documents.

• Make sure you reference in the correct style.
• Double-check your requirements before starting!

If you do that and follow this guide, your ChatGPT references will be perfect.

Learn how to become more productive with our guides on how to use AI.

Thank you for reading this,

Ch David and Daniel

About the author

David, the head editor at Guides.ai, has four years of experience in Artificial Intelligence and Machine Learning. Join David and the team and explore AI tools and contributing to the creation and curation of AI educational content.

• Meta Quest 4
• Google Pixel 9
• Google Pixel 8a
• Apple Vision Pro 2
• Nintendo Switch 2
• Samsung Galaxy Ring
• Yellowstone Season 6
• Recall an Email in Outlook
• Stranger Things Season 5

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

ChatGPT: the latest news, controversies, and tips you need to know

ChatGPT has continued to dazzle the internet with AI-generated content, morphing from a novel chatbot into a piece of technology that is driving the next era of innovation. No tech product in recent memory has sparked as much interest, controversy, fear, and excitement.

What is ChatGPT?

How to use chatgpt, how to use the chatgpt iphone and android apps, is chatgpt free to use, who created chatgpt, what do the chatgpt errors mean, latest chatgpt controversies, can chatgpt be detected, common uses for chatgpt, what are chatgpt plugins, is there a chatgpt api.

• What’s the future of ChatGPT and GPT-5?

ChatGPT alternatives worth trying

Other things to know about chatgpt.

If you’re just now catching on, it’d be fair to wonder what the fuss is all about. You can try it out for yourself for free (or use the official free iOS app ), but here’s the detailed guide you’ve been looking for — whether you’re worried about an AI apocalypse or are just looking for an intro guide to the app.

ChatGPT is a natural language AI chatbot . At its most basic level, that means you can ask it any question, and it will generate an answer.

Using the ChatGPT chatbot itself is fairly simple, as all you have to do is type in your text and receive information. The key here is to be creative and see how your ChatGPT responds to different prompts. If you don’t get the intended result, try tweaking your prompt or giving ChatGPT further instructions. ChatGPT knows the context of previous questions you ask, so you can refine from there rather than starting over fresh every time.

For example, starting with “Explain how the solar system was made” will give a more detailed result with more paragraphs than “How was the solar system made,” even though both inquiries will give fairly detailed results. Take it a step further by giving ChatGPT more guidance about style or tone, saying “Explain how the solar system was made as a middle school teacher.”

• Few people are using ChatGPT and other AI tools regularly, study suggests
• ChatGPT not working? The most common problems and fixes
• Macs just got a huge AI boost

You also have the option for more specific inputting requests for an essay with a specific number of paragraphs or a Wikipedia page. We got an extremely detailed result with the request “write a four-paragraph essay explaining Mary Shelley’s Frankenstein.” And remember, ChatGPT is great at making tweaks to previous answers, so you can always ask for more detail, ask it to rewrite something, or ask it further questions.

To see what it can do, try using ChatGPT in daily life or work activities to see how it can help. Ask it to write emails, craft business proposals, fun date night ideas, or even a best man’s speech. So long as it doesn’t break some of the explicit or illegal content rules, the generator will do its best to fulfill the commands. It’s certainly is potential for ChatGPT to begin filling in gaps with incorrect data. As OpenAI notes, these instances are rare, but AI “hallucinations” certainly do happen . The company also notes that ChatGPT, which uses the GPT-3.5 LLM (large language model), currently has “limited knowledge of world events after 2021.” For more recent knowledge of the world, consider using another tool like Bing Chat .

However, OpenAI recently announced that ChatGPT Plus subscriber, who have access to the GPT-4 model, will be able to search the web for up-to-date information .

Even so, you have the option to input queries continuously until you close your browser or reset the thread to clear your previous requests. These chats are then saved in conversations in the sidebar, even automatically naming the chat. From there, you can manage these chats, renaming or deleting them as needed. You can even “hide” specific chats if needed .

You also have the option to use ChatGPT in dark mode or light mode.

Unlike Bing Chat , which can now generate images with Bing Image Creator and receive images as prompts for questions, ChatGPT only provides text outputs. In September 2023, however, OpenAI added the ability for you to use an image or voice as an input for your prompt. It’s currently only available to ChatGPT Plus subscribers.

As opposed to a simple voice assistant like Siri or Google Assistant , ChatGPT is built on what is called an LLM (Large Language Model). These neural networks are trained on huge quantities of information from the internet for deep learning — meaning they generate altogether new responses, rather than just regurgitating specific canned responses. They’re not built for a specific purpose like chatbots of the past — and they’re a whole lot smarter.

This is implied in the name of ChatGPT, which stands for Chat Generative Pre-trained Transformer. In the case of the current version of ChatGPT, it’s based on the GPT-3.5 LLM. The model behind ChatGPT was trained on all sorts of web content including websites, books, social media, news articles, and more — all fine-tuned in the language model by both supervised learning and RLHF (Reinforcement Learning From Human Feedback). OpenAI says this use of human AI trainers is really what makes ChatGPT stand out.

First, go to chat.openai.com . If it’s your first time, you’ll need to set up a free account with OpenAI before getting started. You have the option of choosing an easy login with a Google or Microsoft account, or just entering your email address. You’ll be asked next to enter a phone number ; however, keep in mind that you cannot use a virtual phone number (VoIP) to register for OpenAI. You will then receive a confirmation number, which you will enter on the registration page to complete the setup.

You’ll see some basic rules about ChatGPT, including potential errors in data, how OpenAI collects data, and how users can submit feedback — all of which have some wondering about whether or not ChatGPT is safe to use . Once you’re through that, you know you have successfully registered. You’re in!

After many months of anticipation, OpenAI has finally launched an official iOS app that you can go and download today . The app quickly topped half a million downloads in less than a week and is becoming available in an increasing number of countries .

Instructions for using it aren’t dissimilar to the ChatGPT web application. You do get an extra option for signing in using your Apple ID account, but it otherwise functions nearly identically to the web app — just type in your question and let the conversation begin.

The clean interface shows your conversation with GPT in a straightforward manner, hiding the chat history and settings behind the menu in the top right.

For those who are paying for ChatGPT Plus, the app lets you toggle between GPT-3.5 and GPT-4 too. You can even use the microphone to chat with ChatGPT over voice.

As our mobile editor noted in his experience with the app, it still doesn’t provide a connection to the internet like chatbots like Bing Chat and Perplexity .

Users have been asking for Android support for months, and now, a ChatGPT Android app is finally available . You can find it in the Google Play Store, but it’s limited to certain countries at the moment, including the U.S., India, and Brazil.

Some devices go beyond just the app, too. For instance, the Infinix Folax is an Android phone that integrated ChatGPT throughout the device. Instead of just an app, the phone replaces the typical smart assistant (Google Assistant) with ChatGPT.

Yes, the basic version of ChatGPT is completely free to use. There’s no limit to how much you can use ChatGPT in a day, though there is a word and character limit for responses .

It’s not free for OpenAI to continue running it, of course. Initial estimates are currently that OpenAI spends around $3 million per month to continue running ChatGPT, which is around $100,000 per day. A report from April indicated that the price of operation is closer to $700,000 per day .

Beyond the cost of the servers themselves, some egregious information has recently come out about what else has been done to train the language model against producing offensive content.

OpenAI also has a premium version of its chatbot, called ChatGPT Plus . It costs $20 a month but provides access even during peak times, faster responses, and first access to new features like GPT-4 .

ChatGPT was created by an organization called OpenAI, a San Francisco-based AI research lab. The organization started as a non-profit meant for collaboration with other institutions and researchers, funded by high-profile figures like Peter Thiel and Elon Musk.

OpenAI later became a for-profit company in 2019 and is now led by its CEO, Sam Altman. It runs on Microsoft’s Azure system infrastructure and is powered by Nvidia’s GPUs, including the new supercomputers just announced this year . Microsoft has invested heavily in OpenAI too, starting in 2019.

Many people attempting to use ChatGPT have been getting an “at capacity” notice when trying to access the site . It’s likely behind the move to try and use unofficial paid apps, which have already flooded app stores  and scammed thousands into paying for a free service.

Because of how much ChatGPT costs to run, it seems as if OpenAI has been limiting access when its servers are “at capacity.” It can take as long as a few hours to wait out, but if you’re patient, you’ll get through eventually. Of all the problems facing ChatGPT right now, this had been the biggest hurdle for keeping people from using it more. In some cases, demand has been so high that ChatGPT has gone down for several hours for maintenance multiple times over the past few months.

This seems to be less of a problem recently, though, as demand has normalized and OpenAI has learned to manage the traffic better, but in the middle of the day, it still makes an appearance from time to time.

Although ChatGPT is a very useful tool, it isn’t free of problems. It’s known for making mistakes or “hallucinations,” where it makes up an answer to something it doesn’t know. A simple example of how unreliable it can sometimes be involved misidentifying the prime minister of Japan .

Beyond just making mistakes, many people are concerned about what this human-like generative AI could mean for the future of the internet, so much so that thousands of tech leaders and prominent public figures have signed a petition to slow down the development. It was even banned in Italy due to privacy concerns, alongside complaints from the FTC — although that’s now been reversed. Since then, the FTC has reopened investigations against OpenAI on questions of personal consumer data is being handled.

Speaking of bans, a number of high-profile companies have been disallowing the use of ChatGPT internally, including Samsung, Amazon, Verizon, and even the United States Congress . Apple is also on the list, though Tim Cook stated that he uses it, just weeks after having it banned .

There’s also the concern that generative AI like ChatGPT could result in the loss of many jobs — as many as 300 million worldwide, according to Goldman Sachs. In particular, it’s taken the spotlight in Hollywood’s writer’s strike , which wants to ensure that AI-written scripts don’t take the jobs of working screenwriters.

Beyond that, multiple controversies have also sprung up around people using ChatGPT to handle tasks that should probably be handled by an actual person. One of the worst cases of this is generating malware, which the FBI recently warned ChatGPT is being used for.

For example, Vanderbilt University’s Peabody School was recently under fire for generating an email about a mass shooting and the importance of community. In addition, JPMorgan Chase is restricting the use of the AI chatbot for workers, especially for generating emails, which companies like Apple have also prohibited internally.

There are also privacy concerns. A recent GDPR complaint says that ChatGPT violates user’s privacy by stealing data from users without their knowledge, and using that data to train the AI model.

Lastly, ChatGPT was even made able to generate Windows 11 keys for free , according to one user. Of course, this is not how ChatGPT was meant to be used, but it’s significant that it was even able to be “tricked” into generating the keys in the first place.

Teachers, school administrators, and developers are already finding different ways around this and banning the use of ChatGPT in schools . Others are more optimistic about how ChatGPT might be used for teaching, but plagiarism is undoubtedly going to continue being an issue in terms of education in the future. There are some ideas about how ChatGPT could “watermark” its text and fix this plagiarism problem, but as of now, detecting ChatGPT is still incredibly difficult to do.

ChatGPT recently launched a new version of its own plagiarism detection tool , with hopes that it will squelch some of the criticism around how people are using the text generation. It uses a new feature called “AI text classifier,” which operates in a way familiar to other plagiarism software. According to OpenAI, however, the tool is still a work in progress and is “imperfect.”

Other tools like GPTZero claim to help detect ChatGPT plagiarism, too. Although they work, some extra editing on AI responses can still trip up these tools.

Well, that’s the fun part. Since its launch, people have been experimenting to discover everything the chatbot can and can’t do — and some of the results have been mind-blowing .

Learning the kinds of prompts and follow-up prompts that ChatGPT responds well to requires some experimentation though. Much like we’ve learned to get the information we want from traditional search engines, it can take some time to get the best results from ChatGPT. If you want to get started, we have a roundup of the best ChatGPT tips .

It really all depends on what you want out of it. To start out, try using it to write a template blog post, for example, or even blocks of code if you’re a programmer.

Our writers experimented with ChatGPT too, attempting to see if it could handle holiday shopping or even properly interpret astrological makeup . In both cases, we found limitations to what it could do while still being thoroughly impressed by the results.

But the fun is in trying it out yourself. Whether you think ChatGPT is an amazing piece of tech or will lead to the destruction of the internet as we know it, it’s worth trying out for yourself to see just what it’s capable of.

Following an update on August 10, you can now use custom instructions with ChatGPT . This allows you to customize how the AI chatbot responds to your inputs so you can tailor it for your needs.

You can’t ask anything, though. OpenAI has safeguards in place in order to “build a safe and beneficial artificial general intelligence.” That means any questions that are hateful, sexist, racist, or discriminatory in any way are generally off-limits.

The announcement of ChatGPT plugins caused a great stir in the developer community, with some calling it “the most powerful developer platform ever created.” AI enthusiasts have compared it to the surge of interest in the iOS App Store when it first launched, greatly expanding the capabilities of the iPhone.

Essentially, developers will be able to build plugins directly for ChatGPT, to open it up to have access to the whole of the internet and connect directly to the APIs of specific applications. It’s ChatGPT out in the real world. Some of the examples provided by OpenAI include applications being able to perform actions on behalf of the user, retrieve real-time information, and access knowledge-based information.

It’s currently only available on a waitlist, but early applications to use plugins with ChatGPT include Expedia, Instacart, Slack, and OpenTable — and now there are lots to explore, including the ones we’ve seen as the best ChatGPT plugins to try out.

Outside of the ChatGPT app itself, many apps had been announced as partners with OpenAI using the ChatGPT API. Of the initial batch, the most prominent example is Snapchat’s MyAI .

Essentially, this is a way for developers to access ChatGPT and plug its natural language capabilities directly into apps and websites. We’ve seen it used in all sorts of different cases, ranging from suggesting parts in Newegg’s PC builder to building out a travel itinerary with just a few words. Recently, OpenAI made the ChatGPT API available to everyone, and we’ve seen a surge in tools leveraging the technology, such as Discord’s Clyde chatbot or Wix’s website builder .

What’s the future of ChatGPT and GPT-5?

There’s no doubt that the tech world has become obsessed with ChatGPT right now, and it’s not slowing down anytime soon. GPT-4, the next iteration of the model, has officially launched, though it’s currently only available for ChatGPT Plus. We do know, however, that Bing Chat is at least partially built on the GPT-4 language model, even if certain elements such as visual input aren’t available.

But the bigger development will be how ChatGPT continues to be integrated into other applications. Microsoft reportedly made a multibillion-dollar investment in ChatGPT , which is already starting to pay off. The first integration was in Teams Premium , with some of OpenAI’s features showing up to automate tasks and provide transcripts. Most prominently, Microsoft revealed 365 Copilot , which integrates ChatGPT natural language prompts directly into Office apps like Word, PowerPoint, Outlook, and more.

There were initial reports that GPT-5 is on the way and could finish training later this year, with some people claiming that it would achieve AGI (artificial general intelligence). That’s a big, controversial statement, but clearly, things are progressing at a rapid pace.

Since then, OpenAI has stated that GPT-5 is not on the timeline and is not currently planned. That being said, the next version, GPT-4.5, is currently training and may be available later this year. OpenAI indicated that it may be done planning as early as September or October.

All that to say, if you think AI is a big deal now, just wait until it’s built into the most common applications that are used for work and school.

ChatGPT remains the most popular AI chatbot at the moment, but it’s not completely without competition. Microsoft’s Bing Chat is the biggest rival, which uses OpenAI’s GPT-4 model as a basis for its answers. Although it requires downloading the Edge browser to use, Bing Chat is free and offers some added features such as different writing modes, image creation, and search links. It even got a significant update recently that introduced features like export, third-party plugins, and multimodal support. There’s also YouChat, which uses GPT-3, an older model from OpenAI, and Forefront AI , which gives you access to GPT-4 and beyond.

The biggest non-GPT competitor to ChatGPT is Google Bard . It’s based on Google’s own homegrown language model, LaMDA, and Google seems intent on competing directly with OpenAI with Google Bard. The most recent updates make it a far more compelling alternative to ChatGPT , even if it’s not quite there.

There are a number of other chatbots out there, some of which are based on Meta’s open-source language model, LLaMA, such as Vicuna and HuggingChat .

Reports suggest Apple has been working on a ChatGPT rival for years , as well, though we haven’t seen it yet. Some reporters say it is “significantly behind competitors” at the moment.

Are ChatGPT chats private?

It depends on what you mean by private. All chats with ChatGPT are used by OpenAI to further tune the models, which can actually involve the use of human trainers. No, that doesn’t mean a human is looking through every question you ask ChatGPT, but there’s a reason OpenAI warns against providing any personal information to ChatGPT.

It should be noted that if you don’t delete your chats, the conversations will appear in the left sidebar. Unlike with other chatbots, individual chats within a conversation cannot be deleted, though they can be edited using the pencil icon that appears when you hover over a chat. When you delete the conversations, however, it’s not that ChatGPT forgets they ever happened — it’s just that they disappear from the sidebar chat history.

Fortunately, OpenAI has recently announced a way to make your chats hidden from the sidebar . These “hidden” chats won’t be used to train AI models either.

When was ChatGPT released?

ChatGPT was originally launched to the public in November of 2022 by OpenAI. The chatbot is based on the GPT-3.5 LLM, which is a fine-tuned version of GPT-3, a model first launched on March 15, 2022. GPT-3 itself, though, has been around for a few years now. It was first released in June 2020, but only as an autoregressive language model.

The predecessors to GPT-3 had very limited public exposure. GPT-2 was announced in February 2019, and the first research paper on GPT was published on OpenAI’s website in 2018.

Will ChatGPT replace Google Search?

Rather than replace it, chatbots are likely to be integrated directly into search. Microsoft has already done this with Bing Chat and Bing, which puts a “chat” tab right into the menu of Bing search.

Even Google has begun experimenting with integrating the smarts of Google Bard into search through its Search Generative Experience . We’re in the early days where all these exist as different products, but it’s not hard to imagine a future where it’s a completely unified experience.

Is Bing Chat the same as ChatGPT?

Microsoft has officially brought ChatGPT to Bing in the form of Bing Chat . After a long beta period, it was officially available to try out. But unlike ChatGPT , Bing Chat does require downloading the latest version of Edge. So Safari or Chrome users are out of luck.

In the early days of its release, Bing Chat was capable of some unhinged responses , but Microsoft has been quick to tame things a bit. It was recently announced that Bing Chat is using the latest GPT-4 language model , meaning it’s more powerful and accurate than ChatGPT . The new Edge Copilot mode also provides a more user-friendly way to get started, offering suggested prompts, links to learn more, and ways to tweak the kinds of answers it gives you. And now with the Windows Copilot , Bing Chat will live right on your desktop.

Is Google Bard the same as ChatGPT?

Unlike Bing Chat, Google Bard  uses an entirely different LLM to power its natural language capabilities. Upon its release, Bard has been using LaMDA, the company’s own model, which stands for Language Model for Dialogue Applications. As has been demonstrated from early on, Bard didn’t have quite the precision in its answers.

Reports indicate, however, that Bard is getting a massive update soon, going from being trained on 30 billion parameters up to 600 billion parameters. That could make it closer to what is possible with GPT-4.

Can you write essays with ChatGPT?

The use of ChatGPT has been full of controversy, with many onlookers considering how the power of AI will change everything from search engines to novel writing. It’s even demonstrated the ability to earn students surprisingly good grades in essay writing.

Essay writing for students is one of the most obvious examples of where ChatGPT could become a problem. ChatGPT might not write this article all that well, but it feels particularly easy to use for essay writing. Some generative AI tools, such as Caktus AI , are built specifically for this purpose.

Can ChatGPT write and debug code?

Absolutely — it’s one of the most powerful features of ChatGPT. As with everything with AI, you’ll want to double-check everything it produces, because it won’t always get your code right. But it’s certainly powerful at both writing code from scratch and debugging code.

Developers have used it to create websites, applications, and games from scratch — all of which are made more powerful with GPT-4, of course. There’s even a plug-in called ChatGPT Code Interpreter that makes programming with AI even more accessible.

What is the ChatGPT character limit?

OpenAI doesn’t set an exact character limit, but it will cut off around its responses at about 500 words or 4,000 characters. If you happen to give the chatbot a request for a specific number of words above 500, you might find that it cuts off mid-sentence somewhere after 500 words.

One way to get around this is just to ask it to “go on” or “continue,” but it depends on the prompt and type of response. Sometimes ChatGPT will more or less repeat the previous answers in different words.

The best way to get access to responses with longer characters is to upgrade to ChatGPT Plus.

Is there a ChatGPT bug bounty program?

Yes. A bug bounty program for ChatGPT was recently announced . The program was unveiled officially on OpenAI’s website , which details the types of “cash awards” that are being offered. They range from $200 to up to $20,000 for what it calls “exceptional discoveries.”

While addressing security researchers interested in getting involved in the program, OpenAI said it recognized “the critical importance of security and view it as a collaborative effort. By sharing your findings, you will play a crucial role in making our technology safer for everyone.”

Do you need to download ChatGPT?

ChatGPT is available via a webpage , so no downloading is needed. However, OpenAI has finally released a free, official iOS app that needs to be downloaded from the iOS app store. For many months, the various app stores were full of fake versions. These are still out there, though, and should be installed and used with caution, as they are not official ChatGPT apps. There is no still no official Android app.

On desktop, there are a couple of ways to install ChatGPT, though. First, you can navigate to the ChatGPT website and save it as a Windows app through Edge. Go to the site, click the ellipsis menu, and hover over Apps.  Select  Install this site as an app  to load ChatGPT from your desktop.

Other tools like MacGPT also allow shortcuts to access the browser service from your desktop.

Can you use ChatGPT on iPhone or Android?

Now that there’s an official iOS app, you no longer have to rely solely on the web app to use ChatGPT on your phone . So, whether with the official app as downloaded through the app store or just the web version, you can certainly use ChatGPT on iPhones. In addition, there’s even a way to replace Siri with ChatGPT on your iPhone, as well as some useful mobile apps like Perplexity AI .

As for Android, you’ll need to rely on the web app. Just as on desktop, type in chat.openai.com to start using ChatGPT.

Can you get ChatGPT to answer any question?

Not exactly. ChatGPT has limitations in the kinds of questions it can answer. First of all, it can’t write about anything that requires internet knowledge after late 2021, which is when its training stopped.

Beyond that, ChatGPT is careful about answering questions that might imply illegal, explicit, or damaging activity. It’ll avoid swearing or political debates, and will (usually) avoid making malware. There is some amount of jailbreaking that can be done to get around these restrictions, but OpenAI is constantly tightening its content policies to restrict unwanted answers. One example of a common jailbreaking technique is the DAN (Do Anything Now) prompt , though OpenAI has worked hard to plug these holes over time.

What is Auto-GPT?

Built on GPT-4, Auto-GPT is the latest evolution of AI technology to cause a stir in the industry. It’s not directly related to ChatGPT or OpenAI — instead, it’s an open-source Python application that got into the hands of developers all over the internet when it was published on GitHub .

With ChatGPT or ChatGPT Plus, the capabilities of the AI are limited to a single chat window. Auto-GPT, at its simplest, is making AI autonomous. It can be given a set of goals, and then take the necessary steps towards accomplishing that goal across the internet, including connecting up with applications and software.

According to the official description on GitHub, Auto-GPT is an “experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM ‘thoughts’, to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.”

The demo used on the GitHub page is simple — just create a recipe appropriate for Easter and save it to a file. What’s neat is how Auto-GPT breaks down the steps the AI is taking to accomplish the goal, including the “thoughts” and “reasoning” behind its actions. Auto-GPT is already being used in a variety of different applications, with some touting it as the beginning of AGI (Artificial General Intelligence) due to its autonomous nature.

What is GPT-4 and how does it compare to GPT-3.5?

GPT-4 is a more advanced LLM — the most powerful that OpenAI currently offers. At the current moment, OpenAI only offers access to GPT-4 through ChatGPT Plus. GPT-3.5, on the other hand, is the LLM that powers the free ChatGPT tool. OpenAI no longer says exactly how many parameters these advanced models are trained on, but it’s rumored that GPT-4 boasts up to 1 trillion parameters.

Regardless, the results are a fairly dramatic difference between GPT-3.5 and GPT-4 in terms of quality. It offers much more precise answers, is significantly better at coding and creative collaboration, and can provide (and respond to) much longer selections of text. GPT-4 remains the best possible model available, while GPT-3.5 is more in line with some other models available.

Who owns the copyright to content created by ChatGPT?

This is a question open to debate. Much of the conversation around copyright and AI is ongoing, with some saying generative AI is “stealing” the work of the content it was trained on. This has become increasingly contentious in the world of AI art. Companies like Adobe are finding ways around this by only training models on stock image libraries that already have proper artist credit and legal boundaries.

According to OpenAI, however, you have the right to reprint, sell, and merchandise anything that was created with ChatGPT or ChatGPT Plus. So, you’re not going to get sued by OpenAI.

The larger topic of copyright law regarding generative AI is still to be determined by various lawmakers and interpreters of the law, especially since copyright law as it currently stands technically only protects content created by human beings.

Editors' Recommendations

• The free version of ChatGPT just got much more powerful
• OpenAI strikes major deal with News Corp to boost ChatGPT
• GPT-4o: What the latest ChatGPT update can do and when you can get it
• ChatGPT can laugh now, and it’s downright creepy
• The best ChatGPT plug-ins you can use

OpenAI needs to watch out because Apple may finally be jumping on the AI bandwagon, and the news doesn't bode well for ChatGPT. Apple is reportedly working on a large language model (LLM) referred to as ReALM, which stands for Reference Resolution As Language Modeling. Made to give Siri a boost and help it understand context, the model comes in four variants, and Apple claims that even its smallest model performs on a similar level to OpenAI's ChatGPT.

This tantalizing bit of information comes from an Apple research paper, first shared by Windows Central, and it appears to be an early peek into what Apple has been cooking for a while now. ReALM is Apple's own LLM that was reportedly made to enhance Siri's capabilities; these improvements include a greater ability to understand context in a conversation.

The ChatGPT chatbot is an innovative AI tool developed by OpenAI. As it stands, there are two main versions of the software: GPT-4 and GPT-3.5. Toe to toe in more ways than one, there are a couple of key differences between both versions that may be deal-breakers for certain users. But what exactly are these differences? We’re here to help you find out. 

We’ve put together this side-by-side comparison of both ChatGPT versions, so when you’re done reading, you’ll know what version makes the most sense for you and yours. What are GPT 3.5 and GPT-4?

ChatGPT, the AI-powered chatbot that went viral at the start of last year and kicked off a wave of interest in generative AI tools, no longer requires an account to use.

Its creator, OpenAI, launched a webpage on Monday that lets you begin a conversation with the chatbot without having to sign up or log in first.

5 Things To Know About ChatGPT

Generative ai tools and resources at ut-austin.

ChatGPT is one of many generative AI tools now being used in educational contexts. We expect that new tools designed for specific purposes and applicable to different disciplinary contexts will be rapidly emerging in the near future. To that end, this resource, focused on ChatGPT, is designed to be adapted to fit different tools and pedagogical approaches. The CTL will continue to update our site with links to UT resources, News articles focusing on generative AI tools, and outlines of suggested approaches to adopting these tools. 

The following is a list of existing UT resources. We will continue to add to this list as new resources are developed. 

• Recommended Practices for Requiring the Use of Generative AI in the Classroom : The Office of Academic Technology (OAT) and the Office of Academic Affairs have developed recommendations for instructors who wish to require the use of generative AI tools in their classrooms. This guidance will be updated on an ongoing basis. If you have questions about these recommendations, please contact the OAT at  [email protected] .
• Addressing the Limitations of Using Generative AI for Learning : The Office of Academic Technology (OAT) has developed a set of guidelines for evaluating the limitations of generative AI tools. 
• Acceptable Use of ChatGPT and Similar AI Tools : This policy-based resource, from the Information Security Office (ISO) at UT-Austin, provides guidance on how to use generative AI Tools safely, without putting institutional, personal, or proprietary information at risk
• Statement on Artificial Intelligence (AI) Tools in Art & Design Courses : Developed by the AI Tools in Education Taskforce, Arts and Design faculty subcommittee at UT Austin, this document includes resources on best practices for instructors specific to the adoption and use of tools in their classrooms, including syllabus script recommendations.
• Statement on Artificial Intelligence in Writing Flag Classes : The Faculty Writing Committee in the Center for the Skills and Experience Flags has been reviewing ChatGPT in light of other writing-related AI tools such as grammar checkers, plagiarism detection services, and automated citation systems. This resource is a summary of the committee's guidance, followed by a fuller discussion of high-level key points. Suggestions are grounded in essential writing pedagogy for the use of AI, including chatGPT, in the writing classroom.
• Texas McCombs' Instructional Innovation Resources : Developed by the the McCombs School of Business, this Canvas resource provides guidance on integrating technology into courses. It contains a rich set of resources and recommendations for ChatGPT/Generative AI. 
• "Reconsider ChatGPT for Academic Use" ( Daily Texan , February 16, 2023): This article offers the perspective of several students on the use of ChatGPT and generative AI tools. 
• Summer 2023 Webinars Recordings : Playlist of Summer 2023 CTL sessions on ChatGPT and GenerativeAI 

While questions about the impact of artificial intelligence in higher education are not new, the emergence of a new tool called ChatGPT that uses increasingly popular chatbot technology to generate human-like, long-form writing has opened the door to new curiosities and concerns.

This document provides suggestions for instructors who wonder how this tool may affect their course design and teaching. The content has been generated by our team, our campus community, and nationally/internationally recognized teaching and learning professionals. Please note this is a rapidly evolving issue with new perspectives, articles, and resources emerging regularly. CTL will continue to monitor developments and share them with the campus community as we are able, as well as create new resources and opportunities for interactions to guide our collective thinking.

1. What is ChatGPT? How does it work?

ChatGPT is a type of artificial intelligence model trained to generate coherent, human-like pieces of writing on a given topic. “ChatGPT was optimized for dialogue,” (1) which means users interact with a chatbot in a conversational context, and the chatbot will compose text based upon the user’s prompts. The bot is capable of generating text on a variety of topics and in a variety of styles, “you simply type in a question or give it a command and it generates text for you.” (2)

You may be interested in experimenting with the tool to learn more: https://chat.openai.com   Please be aware that ChatGPT is “free” because it collects information from its users (e.g., when and how users interact with the tool, users’ IP address, browser type, time zone, type of device, operating system, and country) and may share information with third-party vendors and affiliates (3). For those reasons, we suggest you avoid submitting any sensitive or personal information. In addition, we suggest you review the privacy policy and terms of service with students as a learning exercise.

For more information about ChatGPT, our colleague from the Office of Academic Technology Dr. Juile Schell created this brief video on what ChatGPT is, how to sign up for it, and how it works.

Another helpful resource to learn more about Chat GPT is this presentation developed by Dr. Torrey Trust (U Mass Amherst) that includes a variety of previously submitted prompts and completed output. (4)

2. Why is ChatGPT significant?

Students can enter an assignment prompt and receive a product they can turn in as their work. The text generated by the chatbot could be a well-composed and accurate response depending on the complexity of the assignment and the student’s skill in creating effective prompts. Many higher education instructors and scholars testing the tool report mixed responses, including: 

• ChatGPT-generated papers received B+ to A- minus grades according to a set rubric. 
• A ChatCPT-generated paper did not flag the Turnitin plagiarism detector tool (i.e., no plagiarism was detected).
• ChatGPT chatbot produced grammatically well-written papers relevant to the topic, but struggled with creating detailed responses that demonstrate deep understanding
• ChatGPT was able to do everything asked, including using APA formatting and correct citation; for Nursing content, it was accurate and specific.

In addition, many higher education scholars and practitioners have noted that the tool might be appealing for students in large courses where it can be a challenge to integrate personal approaches to teaching writing and providing in-depth feedback.

3. What are the downsides?

• Submitting personal information to the OpenAI website without an awareness of how the data will be used by OpenAI
• Students not mastering skills needed to succeed, such as audience design, global organization, and researching a topic
• Ethical violations, a lack of integrity
• Uncritical use of digital technologies

At the same time, there is also a downside to banning this technology and neglecting to understand why it was created and the problems it is attempting to solve.

4. Where is ChatGPT going?

The applications of artificial intelligence technology will continue to evolve in ways that currently may not be clear, requiring ongoing conversations focused on ethics, instructional values, and effective pedagogy.

5. What are the implications for UT Austin instructors?

As a first step, learning about this tool will help instructors gain awareness and know to seek assistance when issues related to ChatGPT arise. In addition, the release of ChatGPT encourages us to revisit the best ways to assess student learning in a variety of instructional contexts (5). It invites us to ask important questions, such as:

• Why and how do we best equip students as strong writers?
• What other ways can students demonstrate learning in addition to written papers? 
• What is the best way to solicit student writing that is meaningful and authentic?
• If students rely on ChatGPT as a source of information to answer factual questions, how will that affect their development of research skills?

This focus on the relationship between students and instructors and the educational mission of the university fits with broader efforts underway to reinforce the importance of the process of learning, including making and correcting mistakes. The university is in the process of refreshing our honor code and honor code affirmation to renew our commitment to supporting students in their journey to master complex knowledge and skills. 

With these types of questions and issues in mind, we have gathered a variety of suggestions you can pick and choose to incorporate in your teaching practice if students’ use of ChatGPT is relevant for you.

Incorporating one or two of the following approaches may help ease concerns and challenges that could arise with the introduction of the ChatGPT tool:

As you get ready to begin your class by preparing course documents and resources, make sure that you address appropriate or inappropriate uses of generative AI tools such as ChatGPT in a section of your syllabus. You may choose to place it within or near statements address academic integrity. Please explore the Provost's "Your Syllabus at UT Austin" website as well as UT's Student Conduct and Academic Integrity site for additional options and resources.  

As you craft your syllabus statements, you may wish to adopt one of the following three models and use them as templates: 

"The use of artificial intelligence tools (such as ChatGPT) in this class:

• …is strictly prohibited. This includes using AI to generate ideas, to outline an approach, to answer questions, to solve problems, or to create original language. All work in this course must be your own or created in group work, where allowed).
• …shall be permitted on a limited basis. You will be informed as to the assignments for which AI may be utilized. You are also welcome to seek my prior-approval to use AI writing tools on any assignment. In either instance, AI writing tools should be used with caution and proper citation, as the use of AI should be properly attributed. Using AI writing tools without my permission or authorization, or failing to properly cite AI even where permitted, shall constitute a violation of UT Austin’s Institutional Rules on academic integrity.
• …is permitted for students who wish to use them, provided the content generated by AI is properly cited.

If you are considering the use of AI writing tools but are unsure if you are allowed or the extent to which they may be utilized appropriately, please ask."

For additional suggested syllabi statements, please visit our CTL webpage that contains a range of different statements that you may use and adapt.

• Be clear on what you want your students to know and be able to do or demonstrate by the end of the course and why that knowledge is valuable to their lives. (See this resource for assistance in developing learning outcomes for your course.) Help students see that the ways you are assessing their learning are key to understanding what they are gaining from the course and where they may need extra coaching and support. (6)
• In particular, “If you can explain to students the value of writing, and convince them that you are genuinely interested in their ideas, they are less likely to reach for the workaround.” (7)
• Have an open discussion with your students about the ethical implications of ChatGPT and the value of authentic learning for students’ lifelong development as learners. This may include having conversations around digital literacy and bias in research and scholarship, as AI writing tools like ChatGPT are limited to the public source material they have access to on the internet. Don’t feel you have to have all of the answers, as this is a continually evolving issue. (6)
• Ask students to reference and/or cite class materials, notes, and sources ( particularly sources that are normally behind paywalls but available through the UT Libraries subscription databases and journals. ) in their written assignments. This instruction is valuable because ChatGPT draws on text models from public websites.
• “Require students to reflect more deeply and critically on course topics. This tip is always a good assessment strategy and ChatGPT currently performs better on more superficial and less detailed responses.” (8)
• Use in-class time for students to demonstrate knowledge and understanding in a variety of ways through low-tech, low stakes in-person activities like freewriting and live presentations.
• Craft an assignment where you generate a ChatGPT output based on a prompt and ask your students to critique the response, indicating where it did a good job of articulating key points and what nuances it missed. (For 10 other ways to creatively use ChatGPT in course assignments, see “Update your course syllabus for ChatGPT” ; keep in mind that asking students to engage with ChatGPT may generate privacy concerns, so it may be better practice to provide them with a copy of ChatGPT responses that they can use.)
• Give a hug: empathy, collaboration, communication, and leadership skills;
• Solve a mystery: generating questions and problem finding; and
• Tell a story: finding what's relevant in a sea of data or applying values, ethics, morals, or aesthetic principles to a situation. (9)
• Carefully scaffold assignments with time and space for students to complete each step along the way, and consider whether the number of time-intensive tasks might require more bandwidth than students have to spend. Students are more likely to utilize a tool like ChatGPT when they are short on time. (6)
• Treat ChatGPT as a tool that some students may want to use to help get started writing. For example, students who have difficulty starting writing assignments might be encouraged to generate a paragraph with ChatGPT as a stub that enables them to continue writing. As long as the student ultimately adds significant new material and thoroughly edits or ultimately eliminates the output from ChatGPT, they are producing a document that reflects their own work.

One way to help encourage students to make better decisions about using tools such as ChatGPT is to design your classroom climate to engender mastery approaches to learning, which involve a focus on deeply understanding the knowledge and skills rather than simply achieving a particular score on an assessment. In a mastery-oriented classroom, students are more likely to engage in strategies that will help them truly learn the material rather than for the goal of performing a task and receiving a grade for their work.

Three simple tips for encouraging mastery approaches in higher education classrooms include:

• offering flexible evaluation design: consider providing opportunities for students to revise and redo specific portions of assignments; 
• focusing feedback on process and effort: offer feedback oriented toward student effort and their learning processes rather than on high grades and performance relative to others. When possible offer elaborative feedback rather than feedback based simply on correctness.
• building a sense of belonging: discuss, emphasize, and model that making errors and mistakes is part of everyone's learning processes rather than something that only poor performers or people who "don't get it" do.

Larger, Ongoing Issues for UT Austin & Higher Education

UT Austin is putting in place a structure to respond to new developments such as ChatGPT. The Academic Affairs team consists of experts in teaching and learning, assessment, and academic technology. The team also engages with faculty from across campus and welcomes your participation in our activities. This portfolio will convene campus conversations to evaluate investments in tools, technologies, and instructional practices that help us accomplish the objectives articulated in the strategic plan. Excellence in these areas of work can be achieved through strong partnerships and collaborative vision. 

Next Steps for CTL 

• Continue to learn about the tool and stay updated on new developments
• Convene campus conversations to hear from multiple perspectives
• Create resources to support the teaching community
• Identify policies and practices that advance authentic assessment in courses

In-text citations

• ChatGPT FAQ | OpenAI Help Center
• AI ChatGPT Overview.pdf, Center for Teaching and Learning, American University of Armenia
• ChatGPT, Dr. Torrey Trust
• ChatGPT & Education, Dr. Torrey Trust
• What If We Create a Culture of “Transparent Assessment” (AI & AI), Maha Bali
• Update Your Course Syllabus for chatGPT | by Ryan Watkins | Dec, 2022 | Medium
• Will ChatGPT Change the Way You Teach? EdSurge Podcast
• https://utexas.instructure.com/courses/1293240/pages/chatgpt-faculty-resources (unauthorized)
• 3 Things People Can Do In The Classroom That Robots Can't : NPR Ed

Additional resources

• Faculty Writing Committee Statement on AI in Writing Flag Classes
• "Teaching" Newsletter, Jan. 5, 2022, Chronicle of Higher Education
• Some ill-formed thoughts about AI, robot colleagues, resistance, refusal. Anne-Marie Scott
• Teaching Experts Are Worried About ChatGPT, but Not for the Reasons You Think, Beth McMurtrie, Chronicle of Higher Education
• How People Learn II  (See page 121) - Mastery Learning Resources

Acknowledgements:

The content of this document is inspired by the format from the Educause “7 Things You Should Know About” series.

In addition, many of the perspectives and strategies shared in this document were formed through conversation with our colleagues on campus who support teaching and learning at UT, including Brandon Campitelli, Mary Crawford, Linda Neavel Dickens, Rachelle (Shelly) Furness, Mario Guerra, Jeannette Herman, Kristie Loescher, Art Markman, Michele Ostrow, Julie Schell, George Schorn, and Sean White. We are grateful for this growing network of partners that help us respond to rapid changes affecting higher education.

• Essay Editor

Will I Get Caught Using Chat GPT?

ChatGPT has been around for a little over a year but already found popularity among all groups of users. School and college students have taken a particular liking to it. However, many students avoid using the chatbot for fear that their teacher might catch them.

Read this article to learn more about ChatGPT, its features, and whether your teacher can actually find out if you use it for your homework.

What is Chat GPT?

ChatGPT was first introduced to the world in November 2022. At the time, it was a one-of-a-kind chatbot that used the power of generative AI to create content in response to specific prompts. In simpler words, ChatGPT can analyze your questions and use its vast database of texts to write a cohesive reply.

Before it was introduced to the public, the AI was trained on a massive amount of text sources. Slowly but surely, it “learned” how language works. Now, it can “speak” using this knowledge, repeating the patterns it learned and predicting how the next part of its response should go word by word.

This technology revolutionized the whole globe and opened a new world of opportunities to users from different backgrounds.

Chat GPT: Applications and main features

As a text-based model, ChatGPT can be used across many domains. Let’s explore the main capabilities of Chat GPT and its applications in real life.

• Content creation . ChatGPT can create completely new texts based on a user’s prompt. This is a particularly useful feature for businesses that have to generate a lot of content like ad texts, social media, blog posts, video scripts, etc.
• Research . ChatGPT can use its enormous database to find answers to specific research questions or provide brief overviews of certain sources. It can also give a list of references that researchers are welcome to study further for a more in-depth analysis.
• Translation . ChatGPT can translate texts into over 50 different languages. It can also provide feedback and proofread existing translations.
• Consulting . It’s possible to use ChatGPT for various consultations. Most users prefer asking their questions to the chatbot instead of sorting through myriad web pages selected by search engines. Also, Chat GPT helps users brainstorm ideas, acts as customer support, and even gives basic mental health counseling.
• Proofreading . You can ask the AI chatbot to check your texts or translations for any grammar mistakes. It can in turn give you suggestions to improve your text even more.

As you can see, the capabilities of Chat GPT extend to a wide range of areas, and this is just a small portion of what it can do. It’s also safe to say that the true potential of GPT technology is yet to be explored.

Can I get caught using ChatGPT?

Given how quickly OpenAI’s chatbot took over the world, it’s not surprising that students have already discovered all the benefits of using generative AI for homework. However, there is a common concern that AI writing can be detected by teachers and professors. So, is it true?

Unfortunately, the answer is yes. Texts produced by ChatGPT have several distinct features of texts that experienced educators can easily detect. Besides, there already are a lot of automatic services that can analyze your essays and find traces of ChatGPT origin. Here is a list of these features that are often attributed to AI generators.

• Repetitive patterns . While ChatGPT was trained on a large dataset of texts, it can still use repetitive phrases, particularly in specific contexts. This repetition can become very obvious in longer texts like essays.
• Unusual phrasing . AI may generate sentences or phrases that sound slightly off or unnatural to human readers, which can be caused by low-quality training data or errors in the way the model understands the language.
• Lack of emotion . ChatGPT-generated text often lacks the emotional depth that is typical of human writing. No matter how hard we try to stay neutral, our personal biases seep into our writing while AI tends to produce unnaturally dry text. 
• Factual errors . There are a lot of examples when ChatGPT was seen making up non-existent facts. This is the most obvious mistake that can tip your teacher off about your use of AI generators.
• Lack of creativity . AI may produce texts that rely on common language idioms or templates. This can become a hindrance, especially when your assignment is to show off your creative skills.

As you see, detecting ChatGPT can be easy if you know what to look for. That’s why teachers can often tell when you use it to complete your assignments.

How to avoid getting caught using Chat GPT

Thankfully, there are ways to hide that you used Chat GPT help. But they still require some effort on your part.

1. Generate ideas instead of text

Sure, It’s easier to ask ChatGPT to write an entire paper at once. But it’s much safer to use it to brainstorm ideas. Ask it to compile a plan for your essay or think of supporting arguments. Don’t copy everything it writes without editing. Remember that you need to stick to your style of writing.

Search for sources

You can also ask ChatGPT to compile a list of sources for your papers. But always double-check that these sources exist. As we already know, ChatGPT can write factually incorrect texts, so it’s better to study sources yourself. This way, you’ll also be ready should your teacher ask any follow-up questions about your research.

Use Ai-generator Aithor

While ChatGPT was the first AI chatbot, it’s not the best now. There are plenty of new language models that are trained to write specific texts.

AI-generator Aithor is one of these models. Trained on a large database of academic texts, Aithor can generate top-notch essays and research papers that follow the rules of academic writing to a T.

It can also simulate your writing styles and create completely original texts free of plagiarism. Your teachers won’t find out that you used it because AI-generator Aithor uses constantly improving AI detectors that eliminate this risk.

Explore all the advantages of Aithor right now!

The capabilities of Chat GPT are immense, but there’s still a chance that your teachers will detect it. To avoid this, use this chatbot with caution, for instance, to generate ideas, compile a list of references, or proofread your texts. Or try AI-generator AIthor specifically trained to create academic tests and forget about this concern once and for all.

Related articles

How to write reflection essays.

How often do you contemplate how the tapestry of your experiences shapes your thoughts? A reflection paper lets you explore that. It's like deep diving into your life’s precious moments, examining how stories, books, events, or even lectures have influenced your views. This type of academic essay integrates a personal perspective, allowing you to openly express your opinions. In this guide, we will delve into the specifics of reflective writing, share some tips, and show some self-reflection es ...

Biographical Essay: Tips and Tricks for Writing a Perfect Biography

Biographical essays are some of the most common texts you can find on the Internet. When you browse a Wiki article about your favorite singer, you are basically reading a biography paper. However, in academia, there are certain rules students need to follow to get perfect marks for their papers. In this article, we will explore what a biographical essay is, why it matters, and how to write an essay about a person. What is a biographical essay? A biographical essay is a paper that focuses on ...

APA or MLA: Choosing the Right Citation Style for Your Paper

When it comes to academic writing, properly citing your sources is crucial. It not only helps you avoid plagiarism but also adds credibility to your work by showing that you've done your research. However, with various citation styles out there, it can be tricky to know which one to use. Two of the most common styles are APA (American Psychological Association) and MLA (Modern Language Association). In this article, we'll take a closer look at the APA vs MLA format to help you decide which is ri ...

How to Write an Evaluation Essay That Engages and Persuades: Helpful Tips and Inspiring Examples

Are you feeling unsure about how to effectively evaluate a subject from your own perspective in an evaluation essay? If you're struggling to understand how to present a balanced assessment, don't worry! We're here to guide you through the process of writing an evaluation that showcases your critical thinking skills. What Is an Evaluation Essay?  An evaluation essay is a type of writing in which the writer gives their opinion on a topic. You look at something carefully and think about how good ...

Literary Analysis Essay Example: Discover How to Analyze Literature and Improve Your Writing Skills

Creating a literary analysis essay is one of the most interesting assignments during college and high school studies. It needs both good text interpreting and analytical skills. The number of proper forms is great, including short stories and novels, poems and ballads, comedies and dramas. Any literary work may be analyzed. In brief, when writing this paper a student should give a summary of the text and a detailed review of the language, structure, and other stuff the author used to express hi ...

Create a Perfect Essay Structure

Hello Aithors! We're back again with another feature highlight. Today, we want to talk about a tool that can be a game-changer for your essay writing process - our Table of Contents tool. Writing an essay isn't just about getting your ideas down on paper. It's about presenting them in a clear, structured way that makes sense to your reader. However, figuring out the best structure for your essay can sometimes be a tough nut to crack. That's why we developed the Table of Contents feature. The b ...

Ace Your Graduation Speech with Aithor

Hello, Aithors! Can you feel it? That's the buzz of graduation season in the air:) And while we're all about the caps flying and the proud smiles, we also know that being asked to write a graduation speech can feel a bit like being handed a mountain to climb. Crafting a graduation speech is all about capturing the spirit of the journey you've been on, from the triumphs to the trials, and everything in between. It's a reflection of where you've been, and a beacon of light pointing towards where ...

Proposal Essay Examples: Convincing Ideas for Your Research Paper or Essay

Struggling to craft a captivating and well-built proposal essay? Many students find it challenging to compose a proposal-based essay and struggle to generate convincing ideas. If this sounds familiar, read on. In this comprehensive guide, we streamline the process of brainstorming and composing work, offering resources like suggestions on how to write a proposal essay, suggested steps when writing, useful examples, and efficient essay-crafting tips. Developed through several years of expertise ...

Exploring Students’ Generative AI-Assisted Writing Processes: Perceptions and Experiences from Native and Nonnative English Speakers

• Original research
• Open access
• Published: 30 May 2024

Cite this article

You have full access to this open access article

• Chaoran Wang   ORCID: orcid.org/0000-0002-4140-2757 1  

441 Accesses

Explore all metrics

Generative artificial intelligence (AI) can create sophisticated textual and multimodal content readily available to students. Writing intensive courses and disciplines that use writing as a major form of assessment are significantly impacted by advancements in generative AI, as the technology has the potential to revolutionize how students write and how they perceive writing as a fundamental literacy skill. However, educators are still at the beginning stage of understanding students’ integration of generative AI in their actual writing process. This study addresses the urgent need to uncover how students engage with ChatGPT throughout different components of their writing processes and their perceptions of the opportunities and challenges of generative AI. Adopting a phenomenological research design, the study explored the writing practices of six students, including both native and nonnative English speakers, in a first-year writing class at a higher education institution in the US. Thematic analysis of students’ written products, self-reflections, and interviews suggests that students utilized ChatGPT for brainstorming and organizing ideas as well as assisting with both global (e.g., argument, structure, coherence) and local issues of writing (e.g., syntax, diction, grammar), while they also had various ethical and practical concerns about the use of ChatGPT. The study brought to front two dilemmas encountered by students in their generative AI-assisted writing: (1) the challenging balance between incorporating AI to enhance writing and maintaining their authentic voice, and (2) the dilemma of weighing the potential loss of learning experiences against the emergence of new learning opportunities accompanying AI integration. These dilemmas highlight the need to rethink learning in an increasingly AI-mediated educational context, emphasizing the importance of fostering students’ critical AI literacy to promote their authorial voice and learning in AI-human collaboration.

Similar content being viewed by others

Examining Science Education in ChatGPT: An Exploratory Study of Generative Artificial Intelligence

Artificial Intelligence (AI) Student Assistants in the Classroom: Designing Chatbots to Support Student Success

Artificial intelligence in higher education: the state of the field

Avoid common mistakes on your manuscript.

1 Introduction

The rapid development of large language models such as ChatGPT and AI-powered writing tools has led to a blend of apprehension, anxiety, curiosity, and optimism among educators (Warner, 2022 ). While some are optimistic about the opportunities that generative AI brings to classrooms, various concerns arise especially in terms of academic dishonesty and the biases inherent in these AI tools (Glaser, 2023 ). Writing classes and disciplines that use writing as a major form of assessment, in particular, are significantly impacted. Generative AI has the potential to transform how students approach writing tasks and demonstrate learning through writing, thus impacting how they view writing as an essential literacy skill. Educators are concerned that when used improperly, the increasingly AI-mediated literacy practices may AI-nize students’ writing and thinking.

Despite the heated discussion among educators, there remains a notable gap in empirical research on the application of generative AI in writing classrooms (Yan, 2023 ) and minimal research that systematically examines students’ integration of AI in their writing processes (Barrot, 2023a ). Writing–an activity often undertaken outside the classroom walls–eludes comprehensive observation by educators, leaving a gap in instructors’ understandings of students’ AI-assisted writing practices. Furthermore, the widespread institutional skepticism and critical discourse surrounding the use of generative AI in academic writing may deter students from openly sharing their genuine opinions of and experiences with AI-assisted writing. These situations can cause disconnect between students’ real-life practices and instructors’ understandings. Thus, there is a critical need for in-depth investigation into students’ decision-making processes involved in their generative AI-assisted writing.

To fill this research gap, the current study explores nuanced ways students utilize ChatGPT, a generative AI tool, to support their academic writing in a college-level composition class in the US. Specifically, the study adopts a phenomenological design to examine how college students use ChatGPT throughout the various components of their writing processes such as brainstorming, revising, and editing. Using sense-making theory as the theoretical lens, the study also analyzes students’ perceived benefits, challenges, and considerations regarding AI-assisted academic writing. As writing is also a linguistic activity, this study includes both native and non-native speaking writers, since they may have distinct needs and perspectives on the support and challenges AI provides for writing.

2 Literature Review

2.1 ai-assisted writing.

Researchers have long been studying the utilization of AI technologies to support writing and language learning (Schulze, 2008 ). Three major technological innovations have revolutionized writing: (1) word processors, which represented the first major shift from manual to digital writing, replacing traditional typewriters and manual editing processes; (2) the Internet, which introduced web-based platforms, largely promoting the communication and interactivity of writing; and (3) natural language processing (NLP) and artificial intelligence, bringing about tools capable of real-time feedback and content and thinking assistance (Kruse et al., 2023 ). These technologies have changed writing from a traditionally manual and individual activity into a highly digital nature, radically transforming the writing processes, writers’ behaviors, and the teaching of writing. This evolution reflects a broader need towards a technologically sophisticated approach to writing instruction.

AI technologies have been used in writing instruction in various ways, ranging from assisting in the writing process to evaluating written works. One prominent application is automatic written evaluation (AWE), which comprises two main elements: a scoring engine producing automatic scores and a feedback engine delivering automated written corrective feedback (AWCF) (Koltovskaia, 2020 ). Adopting NLP to analyze language features, diagnose errors, and evaluate essays, AWE was first implemented in high-stakes testing and later adopted in writing classrooms (Link et al., 2022 ). Scholars have reported contrasting findings regarding the impact of AWE on student writing (Koltovskaia, 2020 ). Barrot ( 2023b ) finds that tools offering AWCF, such as Grammarly, improves students’ overall writing accuracy and metalinguistic awareness, as AWCF allows students to engage with self-directed learning about writing via personalized feedback. Thus the system can contribute to classroom instruction by reducing the burden on teachers and aiding students in writing, revision, and self-learning (Almusharraf & Alotaibi, 2023 ). However, scholars have also raised concerns regarding its accuracy and its potential misrepresentation of the social nature of writing (Shi & Aryadoust, 2023 ). Another AI application that has been used to assist student writing is intelligent tutoring system (ITS). Research shows that ITS could enhance students’ vocabulary and grammar development, offer immediate sentence- and paragraph-level suggestions, and provide insights into students’ writing behaviors (Jeon, 2021 ; Pandarova et al., 2019 ). Scholars also investigate chatbots as writing partners for scaffolding students’ argumentative writing (Guo et al., 2022 ; Lin & Chang, 2020 ) and incorporating Google’s neural machine translation system in second language (L2) writing (Cancino & Panes, 2021 ; Tsai, 2019 ).

Research suggests that adopting AI in literacy and language education has advantages such as supporting personalized learning experiences, providing differentiated and immediate feedback (Huang et al., 2022 ; Bahari, 2021 ), and reducing students’ cognitive barriers (Gayed et al., 2022 ). Researchers also note challenges such as the varied level of technological readiness among teachers and students as well as concerns regarding accuracy, biases, accountability, transparency, and ethics (e.g., Kohnke et al., 2023 ; Memarian & Doleck, 2023 ; Ranalli, 2021 ).

2.2 Integrating Generative AI into Writing

With sophisticated and multilingual language generation capabilities, the latest advancements of generative AI and large language models, such as ChatGPT, unlock new possibilities and challenges. Scholars have discussed how generative AI can be used in writing classrooms. Tseng and Warschauer ( 2023 ) point out that ChatGPT and AI-writing tools may rob language learners of essential learning experiences; however, if banning them, students will also lose essential opportunities to learn how to use AI in supporting their learning and their future work. They suggest that educators should not try to “beat” but rather “join” and “partner with” AI (p. 1). Barrot ( 2023a ) and Su et al. ( 2023 ) both review ChatGPT’s benefits and challenges for writing, pointing out that ChatGPT can offer a wide range of context-specific writing assistance such as idea generation, outlining, content improvement, organization, editing, proofreading, and post-writing reflection. Similar to Tseng and Warschauer ( 2023 ), Barrot ( 2023a ) is also concerned about students’ learning loss due to their use of generative AI in writing and their over-reliance on AI. Moreover, Su et al. ( 2023 ) specifically raise concerns about the issues of authorship and plagiarism, as well as ChatGPT’s shortcomings in logical reasoning and information accuracy.

Among the existing empirical research, studies have explored the quality of generative AI’s feedback on student essays in comparison to human feedback. Steiss et al. ( 2024 ) analyzed 400 feedback instances—half generated by human raters and half by ChatGPT—on the same essays. The findings showed that human raters provided higher-quality feedback in terms of clarity, accuracy, supportive tone, and emphasis on critical aspects for improvement. In contrast, AI feedback shone in delivering criteria-based evaluations. The study generated important implications for balancing the strengths and limitations of ChatGPT and human feedback for assessing student essays. Other research also examined the role of generative AI tools in L1 multimodal writing instruction (Tan et al., 2024 ), L1 student writers’ perceptions of ChatGPT as writing partner and AI ethics in college composition classes (Vetter et al., 2024 ), and the collaborative experience of writing instructors and students in integrating generative AI into writing (Bedington et al., 2024 ).

Specifically with regard to classroom-based research in L2 writing, Yan ( 2023 ) examined the use of ChatGPT through the design of a one-week L2 writing practicum at a Chinese university. Analyzing eight students’ classroom behaviors, learning logs, and interviews, the study showed that the use of generative AI helped L2 learners write with fewer grammatical errors and more lexical diversity. The study also found that the students’ biggest concerns were the threat to academic honesty and educational equity. This study is a pioneer in exploring students’ strategies and engagement with ChatGPT in writing; however, it was only conducted through a one-week practicum which did not involve authentic writing assignment tasks. Furthermore, students’ use of ChatGPT was limited to editing AI-generated texts instead of incorporating AI in a wider range of writing activities such as pre-writing and revising human generated texts. In another study by Han et al. ( 2023 ), the authors designed a platform that integrated ChatGPT to support L2 writers in improving writing quality in South Korea. Analyzing 213 students’ interaction data with the platform, survey results, as well as a focus group interview with six students and one instructor, the study found that the students generally held positive experiences with ChatGPT in supporting their academic writing. Although the study undertook a more extensive investigation involving a larger poll of participants with authentic writing assignments, it only explored generative AI’s role as a revision tool without examining its use across various stages of writing. Furthermore, participants in this study were tasked with engaging with a ChatGPT embedded platform of predefined prompts designed by the researchers. Consequently, how students interact with ChatGPT in natural settings remains largely unknown for researchers and educators.

2.3 Writing Process

Since the early 1980s until now, scholars have proposed various writing process models (e.g., Abdel Latif, 2021 ; Flower & Hayes, 1981 ; Hayes, 2012 ; Kellogg, 1996 ), yet they are still trying to form a complete understanding of composing processes. Despite the distinct specific aspects that different models highlight in the writing process, they all negate writing as a linear, sequential process of simply a text generation labor, but emphasize the non-linear and recursive nature of the writing process. Abdel Latif ( 2021 ) noted that various components of writing process such as ideational planning, searching for content, and revising interact with each other, and that both novice and experienced writers employ all of the components but with varying degrees and strategies. For instance, skilled writers refine and revise their ideas during writing, whereas novice writers mostly engage in sentence level changes such as fixing grammatical and lexical issues (e.g., Khuder & Harwood, 2015 ). For L2 students, writing can be very complex and cognitively daunting (Mohsen, 2021 ) due to reasons including but not limited to linguistic barriers (Johnson, 2017 ). Furthermore, writing is more than a cognitive process, it is also a social, cultural, and situated activity. For instance, the concept of plagiarism may carry different meanings and consequences across different cultural contexts. Thus, writing should be investigated in consideration of its dynamic interplay with institutional, cultural, and technological factors (Atkinson, 2003 ).

Considering the intricate nature of writing as a cognitive and social activity, it is thus important to investigate how generative AI may impact the different components of students’ writing processes. However, there is still a substantial gap in knowledge and research about students’ real-world integration of AI into their writing workflows, their decision-making processes, and the rationale behind their decision making while they interact with generative AI and utilize the technology in their writing in formal educational settings. While previous studies shed light on the impacts of generative AI on English writing, empirical classroom-based research remains limited. To further understand how students, both L1 and L2 writers, engage with generative AI in real-life classroom contexts, with authentic writing tasks, and throughout their various processes of writing, the current study thus undertook a naturalistic, exploratory direction that focused on how college students utilized ChatGPT in a first-year writing class in the US. Understanding and unpacking students’ AI-assisted writing processes could help educators better adjust their pedagogy in the face of the growing AI influences. The following research questions guided the present study:

How do students utilize ChatGPT in their writing processes?

How do student writers perceive the benefits of integrating ChatGPT into their writing?

What concerns and limitations do students experience when using ChatGPT to assist with their writing?

What considerations do students identify as important when engaging in generative AI-assisted writing?

3 Theoretical Framework

This study adopts sensemaking theory as its theoretical lens. Sensemaking has been conceptualized as the process through which individuals make meaning from ambiguous and puzzling situations that happen in their experience (Golob, 2018 ). Some scholars view sensemaking as a cognitive process of managing and processing information. This perspective focuses on the cognitive strategies employed in connecting and utilizing information to achieve the purpose of explaining the world (Klein et al., 2006 ). Alternatively, a socio-cultural orientation towards sensemaking regard it as construction of collective identity through an individual’s ongoing interactions with the educational context (Weick, 2005 ). Poquet ( 2024 ) integrates these two theoretical orientations, proposing that sensemaking encompasses both the individual and the collective, drawing attention to how learners explain the cognitive aspects of their learning as well as the social and cultural factors shape their learning experiences.

According to Poquet ( 2024 ), there are three components of the sensemaking process: (1) An individual’s understanding of the activity, available tools, and the situation is the antecedent of sensemaking. (2) Noticing and perceiving constitute the process of sensemaking per se. Noticing involves the identification of salient features of the tool(s) for the activity, while perceiving goes beyond noticing through making sense of the observed, taking into account contextual factors such as learner characteristics and the type of activity undertaken. Perceiving leads to the formulation of meaning and potential implications of what is noticed, playing a critical role in decision-making and action. (3) Outcomes of sensemaking may range from perceived affordances of tools for the activity to casual explanations for the observed phenomena. As defined by Poquet ( 2024 ), sensemaking involves learners crafting explanations for unclear situations through dynamically connecting information within the context of a specific activity. Essentially, sensemaking is both an intentional and intuitive process shaped by how learners understand their environment and their role within it.

Because sensemaking theories aim to examine people’s meaning-making, acting, and experience in “unknown,” “less deliberate,” and “more intuitive” situations (Poquet, 2024 , p. 5), it well aligns with the purpose of this study which is to form an emergent understanding of a less known situation given the relatively new phenomenon of generative AI-assisted writing practices among college students. Adopting a sensemaking lens helps to understand how students make sense of generative AI, how they perceive its affordances, what strategies they develop to use it to assist with their writing, what puzzling experiences they may have, and how they make decisions in those puzzling situations. The dual focus of the cognitive and the social is critical when examining how students engage with and perceive the AI technology and how they negotiate these perceptions and experiences within the learning communities of higher education. Sensemaking theory can also capture the range of individual experiences and shared interpretations among them, elucidating how they deal with uncertainty and make judgments generative AI usage.

4 Research Design

This qualitative study adopted a phenomenological research design, which focuses on understanding and interpreting a particular aspect of shared human experience (Moran, 2002 ; Smith, 1996 ). Phenomenology seeks to form a close and clear account of people’s perceptions and lived experiences as opposed to delivering a positivist conclusion of human encounters, as “pure experience is never accessible” (Smith et al., 2009 , p. 33). In the present study, as there is limited understanding of students’ engagement with ChatGPT in their writing process, a phenomenological lens could help capture participants’ own sense making of their AI-assisted writing experiences.

4.1 Context and Participants

The study took place in spring 2023 at a higher education institution in the US. I chose to focus on first-year writing as the study setting, as it is a required course in most colleges and universities, thus a typical writing and learning context for most college students. First-year writing serves as the foundation for cultivating academic writing skills, with the aim of developing students’ essential literacy and writing proficiency needed for their undergraduate learning experiences. The 14-week course focused on English academic reading, writing, and critical thinking and consisted of three major units.

This study focused on the last unit, which was about argumentative writing, a common type of academic essay writing (American Psychological Association, 2020 ). The final essay asked students to form an argumentative response to a research question of their own choice. The unit, lasting for three weeks, was structured as follows (see Fig.  1 ): During the first week, the instructor spent two classes, each for 75 min, introducing ChatGPT (GPT 3.5) as a large language model and inviting students to explore ChatGPT as a tool for writing. The instructor carefully chose and assigned five readings that allowed the students to grasp the ongoing academic and public debates and concerns regarding the use of ChatGPT in writing and educational settings. During the class sessions, students participated in various activities exploring the functionalities of ChatGPT, discussed ethics and academic integrity, and critiqued AI-generated writing. As part of the discussions on ethics, the instructor explicitly addressed academic integrity issues drawing upon both the writing program’s guidelines and the institution’s academic integrity policies to ensure that the students were aware of and committed to ethical use of generative AI in the writing class. During the second week, students learned various strategies for integrating sources in academic writing and practiced ways of using sources to build arguments. During the last week, students spent time peer reviewing each other’s work and met with the instructor individually to improve their drafts.

Unit design with key topics and learning tasks over the three weeks

The final essay allowed but did not mandate students to use ChatGPT. For those who used ChatGPT and AI writing tools, disclosure and transparency about how AI was used were required as part of the submission to the assignment. The instructor left using AI in their final essay as an open option to the students themselves, ensuring that students could pursue the option that works best for their individual needs. Thus the unit provided various opportunities and flexibility for planning, researching, drafting, reviewing, and editing with ChatGPT throughout students’ writing process.

There were 11 students, all freshmen, enrolled in the class. All but one reported using ChatGPT in their writing. Six students were recruited based on their willingness to participate and the diversity of their first language to ensure a balanced coverage. Table 1 shows the demographic information of the students (with pseudonyms).

4.2 Data Collection

Aligned with an interpretive phenomenological design that focuses on exploring participants’ lived experiences and how they construct meaning of their own experiences (Smith & Shinebourne, 2012 ), I collected three major types of data in order to uncover the students’ writing processes involving ChatGPT and their perceptions. First, I collected students’ written products and artifacts such as in-class writing, screenshots of students’ conversations with ChatGPT, informal short writing assignments, and the formal writing assignments for the final argumentative essay. Second, I collected students’ written self-reflections about their use of ChatGPT in writing. Finally, the participants were interviewed for around 30–40 min, and all interviews were audio-recorded. These semi-structured interviews were developed around students’ former experiences with ChatGPT, their views of the tool, and the ways they utilized ChatGPT for their writing assignments in this class.

Students’ conversational screenshots with ChatGPT and their in-class and outside class writing drafts could demonstrate their interactions with AI as well as the changes they made upon contemplating the responses from the chatbot. The interviews and students’ self-reflections could further shed light on their perceptions and decision-making. Multiple sources of data helped to understand students’ behaviors, perceptions, and engagement with AI during different stages of writing. Triangulation of the data also helped me to understand students’ rationale for and practices of integrating, discounting, and reflecting on the chatbot’s output into their writing.

It is important to note that a phenomenological qualitative research design like this aims to provide in-depth understanding and insights into participants’ experiences. The context of the study—a first year writing class—and the specific type of assignment investigated are both common scenarios in college classrooms, thereby enhancing the study’s relevance despite its limited sample size and scale. Furthermore, the incorporation of data collected from multiple and diverse sources for triangulation adds to insights into participants’ experiences, which helps strengthen the credibility of the study.

4.3 Data Analysis

Thematic analysis (Creswell, 2017 ) was used to analyze the written drafts and transcriptions of interview data as it is commonly used in qualitative studies to identify patterns across various types of data (Lapadat, 2012 ). While transcribing all the interview data verbatim into written scripts, I took notes with the research questions in mind. Then I organized and read through the various types of written data to get familiar with and form a holistic impression of participants’ perceptions and experiences of AI-assisted writing. The coding, conducted on Nvivo, a qualitative data analysis software, followed an inductive and iterative process. During the first cycle of coding, I reviewed the data line-by-line and applied in vivo coding to generate initial, descriptive codes using participants’ voices (Saldaña, 2016 ). For the second cycle, I identified patterns across the in vivo codes and synthesized them into 20 pattern codes (Saldaña, 2016 ). During the third cycle, I clustered and grouped the pattern codes into four emerging themes. To finalize and refine the themes, I double checked themes, codes, and the supporting data guided by the research questions. Table 2 shows the themes and pattern codes. To ensure the trustworthiness of the qualitative analysis, I also conducted a peer debriefing (Lincoln & Guba, 1985 ) on the codebook with an experienced qualitative researcher. Furthermore, member check was also conducted with each participant via email to minimize the possible misinterpretations of their perceptions and experiences.

5.1 How Do Students Utilize ChatGPT in Their Writing Processes?

The students reported using ChatGPT throughout different components of writing their argumentative essays including (1) brainstorming, (2) outlining, (3) revising, and (4) editing.

In terms of brainstorming, the students acknowledged the value of ChatGPT in helping them get initial ideas and inspirations prior to the research phase for their essays. For instance, Lydia was interested in writing about the cause of the low fertility rate in South Korea but she “had trouble thinking of any focus areas” (Lydia, Reflection). In order to narrow down the topic and find a good focus, she used ChatGPT for exploring possible directions she could pursue. As she noted:

It immediately gave me suggestions to approach the cause from demographic changes, economic factors, traditional gender roles, governmental policies, and cultural attitudes with detailed explanations beside each suggestion. So, I went on to pick economic reasons, which I think were the most accessible to write about. (Lydia, Reflection)

ChatGPT’s feedback facilitated a smoother decision-making process for Lydia regarding the specific topic to further investigate. Another student Kevin mentioned that running his initial research idea into ChatGPT was helpful because ChatGPT gave him “some relevant ideas that hadn’t crossed his mind when thinking about the topic” (Kevin, Written Assignment).

Considering ChatGPT’s suggestions did not mean that the students just took them for granted and incorporated them unquestioningly. For instance, Nora was interested in writing about the impact of AI on human lives. Upon putting her initial research question into ChatGPT, she found the feedback helpful and decided to do more research on the aspects highlighted by ChatGPT (see Fig.  2 ).

Screenshot of Nora’s conversation with ChatGPT

Students also reported using ChatGPT for outlining. Emma used ChatGPT extensively to help organize her outline and shared her procedure as follows:

I wrote my own outline first consisting of my own ideas and then put it into ChatGPT. I asked ChatGPT to make the outline flow better. I was surprised with the results it gave me. It made the ideas more concise and connected better off of each other...I tried it a few times, and every time it gave me a different version of the outline that I could potentially use. I ultimately compared the information from my sources and chose an outline I thought best suited my essay and my essay question. (Emma, Reflection)

Emma’s approach revolved around utilizing ChatGPT to unearth linkages among her various initial yet disorganized ideas she already had. By experimenting with diverse ways to build coherence and connection among her thoughts with the aid of AI, she shortcut the mental task of structuring her ideas from scratch.

Using ChatGPT for refining the flow of ideas was also a strategy adopted by other students, but not always during the outlining stage. For instance, after completing her first draft, Lydia “copied and pasted her entire essay into the chatbox and asked for suggestions on how to improve the structure and argument” (Lydia, Reflection). Lydia underlined that her revision process with ChatGPT was iterative, as she put her revised version back into the chatbot and went through another round of feedback and subsequent revision. Additional applications reported by students also encompassed employing ChatGPT to reduce redundancy and enhance conciseness of content (Emma) as well as to refine topic sentences for accurately summarizing the main ideas of body paragraphs (Kevin).

Apart from utilizing ChatGPT to assist with global level issues such as structure, argument, and coherence, the students also harnessed the AI tool for sentence-level issues. They unanimously agreed that ChatGPT was a valuable tool for language editing. Alex, a L1 student, commented that ChatGPT could edit essays “exceptionally well.” Alex not only used the AI tool to help improve the syntax of his writing such as “run-on sentences” but also consulted it as his dictionary for “providing academic diction” (Alex, Interview). The L2 participants particularly acknowledged ChatGPT as beneficial for enhancing the accuracy of their writing. Lydia shared that upon completing a paragraph of her essay, she would put it into ChatGPT and ask it to “revise the wording and grammar only” so she could refine her language and keep the content original (Lydia, Reflection). Another L2 student Nora noted that “when I struggle with expressing my thoughts accurately in English words, ChatGPT can help me express those ideas in a more powerful and accurate way. It removes communication barriers” (Nora, Written Assignment).

5.2 How Do Student Writers Perceive the Benefits of Integrating ChatGPT into Their Writing?

Utilizing ChatGPT in their various writing process components, the students reported that ChatGPT had the following benefits: (1) accelerating their writing process, (2) easing their cognitive load, (3) fostering new learning opportunities, (4) getting immediate feedback, and (5) promoting positive feelings about writing.

Students stated that using ChatGPT could “speed up the process of writing” (Alex, Interview) as exemplified by the following quotes: “ChatGPT really helped me to explore the essay topics that I’m interested in within a very short amount of time and identify what can be written about” (Nora, Interview); “I discovered after using it for my final essay that ChatGPT can greatly improve the efficiency of my writing” (Alex, Reflection). For L2 writers, it significantly saved the time they typically spent on editing, as mentioned by Lydia:

As an international student who is not a native English speaker, writing college essays would take me double the amount of time compared to those who write essays in their first language. Oftentimes, the biggest time I spent was on editing the grammar and trying to make my language readable and understandable. (Lydia, Reflection)

The benefits of saving the time and energy on language concerns, grammar, wording, and the organization of ideas and messy drafts, furthermore, reduced the cognitive burden among the student writers, both L1 and L2. For instance, knowing ChatGPT’s editing power, Alex felt that he was able to “focus more on the subject of the writing rather than the language itself” and “spew out thoughts freely” when drafting the essay (Alex, Interview). Likewise, the L2 students noted that ChatGPT allowed them to delay their concerns about the linguistic forms of ideas and alleviate the demanding cognitive load associated with L2 writing. As claimed by Lydia, “It freed my thoughts so that I could spend more time revising the content, but not worry about how to express my ideas for the essay” (Lydia, Interview).

The students conveyed that incorporating ChatGPT in different components of writing also fostered new learning opportunities for them to improve writing. Nora shared that “ChatGPT not only made my language more fluent and comprehensible, but it also helped me to learn new ways of expression in English” (Nora, Interview). Su remarked that although ChatGPT’s feedback was generic, it promoted her to do further research about her topic and learn more writing strategies (Su, Written Assignment).

Students particularly highlighted the “instant and personalized feedback” (Kevin, Reflection) provided by ChatGPT as a strong impetus and benefit. For instance, as a frequent visitor of the school’s writing center, Lydia mentioned she typically scheduled two to three appointments with a writing tutor for each major writing assignment she had worked. With ChatGPT, she could obtain feedback anytime: “Now I don’t have to physically go to the writing center at 11 pm, waiting for the previous visitor to finish their session” (Lydia, Interview). She used “my walking AI tutor” to describe the role of AI in her writing.

Ultimately, the students mentioned that these cognitive and practical benefits of ChatGPT not only improved their efficiency of writing, but also promoted positive feelings about writing. They used words such as “more relieved” (Emma), “sense of accomplishment” (Lydia), and “less anxious” (Nora) to describe the AI-assisted writing process. Although the students expressed different needs and utilization of ChatGPT, they all conveyed that they would like to continue using it in the future.

5.3 What Concerns and Limitations Do Students Experience When Using ChatGPT to Assist with Their Writing?

Despite the benefits and usefulness of ChatGPT for assisting with students’ writing, they also expressed many reservations and limitations regarding the AI tool. The first concern was about the false information it produced and its potential to mislead people. The students commented that ChatGPT tended to “make up information” (Emma), “make assumptions and guesses” (Su), and generate “inaccurate information” (Nora), “wrong information” (Alex), and “nonsense” (Lydia). Furthermore, the students pointed out that ChatGPT was inadequate in addressing high-level questions requiring critical thinking, as Su explained: “When I was consulting with ChatGPT, I learned that it has a very limited understanding of the topic I was talking about” (Su, Reflection). Other students also pointed out that the responses they got from ChatGPT could be “very generalized” (Kevin) and lacked “depth and complexity” (Nora).

The next shortcoming of ChatGPT, as noted by the students, is the lack of creativity and originality. Su highlighted that relying on ChatGPT’s ideas would not yield intriguing essays, as even though ChatGPT’s responses may “appear to make sense,” they usually came across as “cliched and superficial.” Su understood that it was because ChatGPT and large language models “work based on the patterns and data they have been trained on and cannot think outside of this” (Su, Reflection). Therefore, it is “not effective in generating new ideas” for an essay (Alex, Interview).

The algorithm unavoidably led to another limitation as observed by the students, which is the lack of reliable evidence and support for the content generated by ChatGPT. Su acknowledged that ChatGPT was not a good source for writing as it was impossible for a reader to trace the original information. Apart from the lack of clarity and transparency about the sources ChatGPT draws upon, Kevin pointed out an additional drawback that ChatGPT’s ideas were “not up to date,” thus not a good source for academic writing (Kevin, Written Assignment).

5.4 What Considerations Do Students Identify as Important When Engaging in Generative AI-Assisted Writing?

Presented with these limitations of ChatGPT, the students shared some important aspects they think should be considered when incorporating AI into writing, summarized as follows: (1) balanced and moderate use of AI, (2) critical use of AI, (3) ethical considerations, (4) the need for human voice, (5) the importance of authenticity, (6) seizing AI as a learning opportunity, and (7) transparency from and conversation between teachers and students.

The students worried that over-reliance on ChatGPT would undermine their writing ability, so they should use ChatGPT to a balanced and moderate extent. The students believed that ChatGPT should be used as “guidance,” “support,” “supplement,” and “assistant” (Alex, Reflection) rather than a “substitute” or “replacement” (Su, Reflection).

Furthermore, the students emphasized the importance of critical use of AI. Emma noted that AI platforms could “decline the need to think critically” as some students might want to “take the easy route and just get the answer” (Emma, Interview). They insisted keeping a critical eye on the information AI generated as it was not reliable. To do this, students shared similar strategies which was to use ChatGPT as a departure rather than a destination for writing, thinking, and research. They underscored the importance of validation and critical thinking in this process.

Another facet to consider is the ethical use of AI. The students believed that one must be very careful when using ChatGPT as it can easily walk the line of plagiarism. They deemed acts such as using ChatGPT to generate new ideas and write entire essays unethical, as these are forms of taking credit for other people’s work based on their language and ideas (Kevin, In-Class Writing). Thus students emphasized the importance of “doing research on your own” (Emma), “making sure the ideas are my own” (Lydia), and “not using everything (i.e. sentence by sentence, word by word) provided by ChatGPT” (Su).

The students also regarded the issue of retaining human voice a pivotal consideration for AI-assisted writing. They pointed out that writing should be a means to express the writer’s identity and thoughts, but AI was not able to personalize the text to their individual style and voice. Wary of the threat posed by extensive adoption of ChatGPT to individual expressions, Lydia commented, “ChatGPT tended to use similar dictions and patterns of wording and sentence structures. If everyone uses ChatGPT, our style will become more and more alike” (Lydia, Interview). Similarly, Su pointed out that ChatGPT could make the text “sound generic and impersonal,” which is a problem “when you are trying to convey your own ideas, feelings, and perspectives” (Su, Written Assignment). To “truly present a unique perspective and make writing individualized,” one must “take full control” of their writing to deliver a powerful message (Kevin, Reflection). This process requires the discernment to dismiss advice from ChatGPT to avoid generating an impersonal, blunt style of writing that lacks the writer’s distinct character.

Students also pointed out that the involvement of ChatGPT in writing may not only jeopardize how human voice is conveyed through the ideas ChatGPT generates, but also through the language it produces, thus “ruining the authenticity of an essay” (Alex, Reflection). He questioned himself for a paradoxical use of ChatGPT. On the one hand, he utilized ChatGPT for editing and better academic diction; on the other, he was perplexed and apprehended about the tipping point where the essay would start to sound “more like ChatGPT rather than yourself.” As he explained:

ChatGPT suggested some words I never would have used, and I decided not to include them. While they may obviously sound better than my own authentic words, I just did not feel honest using them. For instance, when writing this paper, ChatGPT suggested I use “judiciously” rather than “in moderation.” I never would have used “judiciously,” and it felt unauthentic to use it. (Alex, Reflection)

The students suggested cautious, strategic, and purposeful use of ChatGPT’s editing features to ensure it amplifies rather than conflicts with their own writing style.

However, boundaries like this still appeared to the students as vague. Hence, the students called for guidelines and instructions in the classroom and open conversation between teachers and students. The students expressed their confusion over the lack of clear guidelines across their classes. As Alex commented, “It’s hard to draw lines with different ways of using ChatGPT and which one would be considered cheating or not” (Alex, Interview). The students hoped that all their instructors, instead of only writing teachers, could engage in comprehensive discussions about what specific ways of using ChatGPT would be regarded as acceptable or problematic according to their disciplinary conventions and learning purposes.

Participants also expected that school policies and instructors would not shut down AI as a resource and learning opportunity for students. Emma said, “It’s tricky as there are a lot of different opinions, but technology is the world we live in. We should go with the grain as opposed to against it” (Emma, Interview). Cautious of possible missed learning opportunities that AI might bring to thinking, Lydia commented, “I am afraid of becoming lazy…But I guess it also depends on how you use it. It gives a shortcut for people who do not want to make the effort to learn and think. But it could be useful for those who really want to learn” (Lydia, Interview). Alex noted that to prevent the loss of learning opportunity, for instance, he decided that rather than taking ChatGPT’s diction suggestion immediately, he “would use those words in the next essay,” demonstrating his effort in learning and internalizing the knowledge. In general, the students were still exploring ways to use ChatGPT in critical, authentic, and ethical ways that would promote rather than harm their learning.

6 Discussion

Adopting sensemaking theory, the study investigated how students made sense of their AI-assisted writing practices, providing insights into students’ learning process and their shared practices emerging around the AI technology. Confirming previous research (e.g., Guo et al., 2022 ; Holmes et al., 2019 ; Su et al., 2023 ), this study found that the students overall had positive experiences with generative AI-assisted writing, for it could accelerate their writing process, reduce their cognitive load and anxiety, and provide prompt feedback. The students integrated ChatGPT into various components of their composing process, such as searching for content, ideational planning, language editing, and revising. Although the students acknowledged the cognitive and affective benefits (e.g., Ebadi & Amini, 2022 ; Fryer & Carpenter, 2006 ) of using ChatGPT in writing, they were very cautious about adopting its ideas and suggestions at different discourse levels (i.e., essay, paragraph, and sentence levels) due to critical, ethical, and authentic concerns. This finding extends previous research which identified that students’ primary concerns were academic dishonesty and educational inequity (Yan, 2023 ). Despite recognizing AI’s limitations such as the lack of in-depth insights (Gao et al., 2022 ), originality, creativity, and reliability—qualities essential for good academic writing—the students deemed it necessary to embrace rather than abandon the tool, with the purpose of fostering one’s critical thinking and writing skills. The results suggest that students’ sensemaking of AI-assisted writing is shaped by their prior knowledge and understanding of writing as a cognitive and sociocultural activity, their exploration of AI’s functionalities and strategies for leveraging them to achieve learning goals, and their interrogation of the appropriateness and limitations of AI in the specific context of academic writing.

The study highlights two emerging dilemmas students experienced in their generative AI-assisted writing processes. The first dilemma, as Alex put it, is the choice between sounding better or sounding like me when integrating AI into the decision making process of writing, reflecting a larger issue about academic integrity, authenticity, and voice in human-AI collaboration. The participants believed that it is crucial to prevent their writing from being AI-nized, which could lead to either plagiarism or a writing style resembling AI that overshadows their own voice—the very essence of their “identity and presentation of the self in writing” (Prince & Archer, 2014 , p. 40). The students’ beliefs align with a connectivism paradigm of AI in Education (AIEd) outlined by Ouyang and Jiao ( 2021 ), in which AI serves as a tool to augment human intelligence and capability (Yang et al., 2021 ) and learner agency is placed at the core. Reliance on AI could lead to superficial engagement with writing tasks, discouraging deeper, reflective thought processes essential for original creative expression. Furthermore, when AI suggests similar vocabulary, structures, and styles to various learners, it risks imposing a uniformity in expression that undermines the educational value of cultivating each individual’s unique and creative voice. AI may hinder students from exploring how language variation and linguistic diversity can be rich resources for meaning-making, creativity, identity formation, problem-solving (Wang et al., 2020 ). Such critical engagement with diverse language resources is crucial for developing students’ literacy skills in a digital age where multicultural awareness is an integral part of education (Sánchez-Martín et al., 2019 ). As Dixon-Román et al. ( 2020 ) noted, educators must be wary of AI’s “racializing forces,” which standardize learning processes in ways that can marginalize non-dominant forms of knowledge and communication, as well as students whose experiences and identities are either not represented or misrepresented in the system.

While the participants concurred that upholding human voice and agency entails possessing integrity and alignment not only at the ideational level but also in the linguistic expression of those ideas, the L2 writers in this study added another nuanced dimension to the impact of AI on human voice and authenticity in the context of AI-assisted writing. As the L2 students experienced, ChatGPT’s language suggestions might not pose a threat to their voice but serve as a catalyst for augmenting their voice, as AI helped overcome their language barriers and better express ideas true to themselves. In other words, generative AI afforded the L2 writers powerful language repertoires that enhanced the accuracy and efficiency of “linguistic rehearing” (Abdel Latif, 2021 ) or “translating” (Kellogg, 1996 ) component of their writing process, thus allowing L2 students to produce writing more authentic to themselves. The finding highlights how learner characteristics and individual differences play an important role in students’ sensemaking of AI-assisted writing, complicating the existing understanding of AI’s affordances for learners with diverse linguistic backgrounds and learning needs.

From earlier conceptualizations of authenticity as “ownedness” and “being one’s own” by Heidegger (1927/ 1962 ), to contemporary perceptions as the “self-congruency” of an individual, group, or symbolic identity (Ferrara, 1998 , p. 70), the notion of authenticity has been evolving and becoming more pluralistic. As Rings ( 2017 ) acknowledged, authenticity extends beyond adherent to personally endorsed commitments; it requires a comprehensive consideration of one’s self-awareness and the changing social context. Scholars should further pursue what it means by authenticity and academic integrity in an increasingly AI-mediated educational context, ways to promote students’ authorial voice and agency, as well as the complicated authorship issues (Jabotinsky & Sarel, 2022 ) involved in AI-human collaboratively generated texts. As Eaton ( 2023 ) claims, it is time to contemplate “postplagiarism” and academic integrity in a future where “hybrid human-AI writing will become normal”.

Apart from the sounding better or sounding like me dilemma experienced by students, another paradox is whether AI caused missed learning opportunities or created new learning opportunities . As noted by the previous literature, AI-writing tools may rob students of essential learning experiences (Barrot, 2023a ; Tseng & Warschauer, 2023 ). Adding to this concern from educators and scholars, the present study shows that the students themselves are also cognizant of the possible learning loss due to AI adoption. Furthermore, the study shows that rather than passively indulging themselves in the convenience of AI tools, a common concern among educators (Chan & Hu, 2023 ; Graham, 2023 ), the student writers attempted to seize new learning opportunities that emerged from AI technologies to promote their critical thinking and writing. This finding suggests a nuanced addition to sensemaking theory: the process of making sense of uncertainties in AI-infused literacy practices can also be uncertain, involving reconciling dilemmas and acknowledging perplexing experiences. While not always yielding clear-out outcomes or casual attributions for the observed phenomena and personal experience as suggested by Poquet ( 2024 ), noticing and perceiving the unpredictable impacts of generative AI on students’ own learning processes can, in itself, be empowering. The process fosters a sense of agency and critical engagement, suggesting that the outcomes of sensemaking in the context of AI-assisted writing can be open-ended yet profound.

This important finding leads scholars to reconsider the essence of learning in an era of generative AI. Hwang et al. ( 2020 ) and Southworth et al. ( 2023 ) argued that AI is likely to transform not only the learning environment, but also the learning process, and even what it means to learn. This perspective finds resonance in the experiences of the participants in this study. While AI may shortcut traditional ways of doing writing, it does not inherently imply a reduction in students’ cognitive, behavioral, and affective engagement with writing, learning, and thinking. AI does not necessarily make writing easier; on the contrary, a critical, ethical, and authentic approach to AI-assisted writing pushes students to think further and prioritize their own voice, originality, and creativity, leading to high quality writing. In this sense, when used properly, AI has the potential to introduce a new avenue for humanizing writing and education. As generative AI technologies are advancing rapidly, an expanding array of AI-powered writing assistance, intelligent tutoring systems, and feedback tools has the promise to cater to the diverse needs and learning styles of language learners and writers. These tools are not limited to mere textual assistance; the multimodal functionalities of generative AI can also allow writers to explore creative expressions and multimodal writing, enriching students’ literacy practices by integrating more visual, auditory, and interactive elements into the composition process (Kang & Yi, 2023 ; Li et al., 2024 ). As noted by Cao and Dede ( 2023 ), our educational model has long been centered around the product , directing our focus towards the outcomes and grades students achieve, often overlooking the learning process itself. The judgmental calls involved in students’ interactions with AI, as showcased in the nuances of participants’ AI-assisted writing process in this study, represent emerging learning opportunities that require students to draw upon a range of knowledge, skills, awareness of ethics and the self, criticality, and self-reflection to make informed decisions about AI in learning. The present study shows that such decision making process can play a pivotal role in cultivating students’ “AI literacy” (Ng et al., 2021 ) and promoting their responsible use of AI. Therefore, it should also be recognized as a valuable teaching opportunity that educators should not overlook.

7 Conclusion

This study explored students’ generative AI-assisted writing processes in a first-year writing class in an American college. The study found that students utilized generative AI for assisting with both global (e.g., argument, structure, coherence) and local issues of writing (e.g., syntax, diction, grammar), while they also had various ethical and practical concerns about the use of AI. Findings showed that large language models offer unique benefits for L2 writers to leverage its linguistic capabilities. The study highlights the urgency of explicit teaching of critical AI literacy and the value of (post)process-oriented writing pedagogy (e.g., Graham, 2023 ) in college writing classrooms so that students not only understand AI writing tools’ functions and limitations but also know how to utilize and evaluate them for specific communication and learning purposes.

However, writing instruction is still at the beginning stage of addressing this pressing need. Thus, pedagogical innovations, policy adjustments, new forms of writing assessments, and teacher education (Zhai, 2022 ) are needed to adapt to the potential impact of AI on desired student learning outcomes within specific writing curriculums. For instance, integrating critical digital pedagogy into writing instruction and inviting students to reflect on their relevant AI literacy practices allow writing instructors to more effectively guide students in critically engaging with AI technologies in their academic literacy development. Policy adjustments should aim to cultivate an inclusive rather than “policing” environment (Johnson, 2023 ) that encourages students to use AI responsibly and as a means of fostering self-learning. Furthermore, writing assessment methods should evolve to not just evaluate final learning outcomes such as the written products but also the learning journey itself such as the decision-making involved in their AI-assisted writing. This shift encourages students to appreciate learning processes and the productive struggles they encounter along the way, so that they can move beyond seeing AI as a shortcut but as assistance in their quest for learning and writing development. In this way, students can leverage the linguistic, multimodal, interactive, and adaptable affordances of generative AI tools for personalized learning. This facilitates greater student ownership of their learning, enhancing their learner competence through self-direction, self-assessment, and self-reflection when interacting with AI tools (Barrot, 2023c ; Fariani et al., 2023 ).

Following a phenomenological research design, the present study aims to provide in-depth understanding of college students’ use of ChatGPT in their academic writing, yet it is limited due to its small sample size and duration. Therefore, the findings may not apply to other classroom contexts and to a wide range of student populations. Future research could benefit from adopting a large scale, longitudinal design to examine generative AI’s impacts on student writing and students’ long-term engagement with generative AI tools, both in formal classroom settings and in informal learning contexts. It is also worth exploring students of diverse age groups and language proficiency levels as well as writing courses of different languages, purposes, and writing genres to examine other factors that may influence students’ generative AI assisted writing. After all, the participants in this study have already developed some proficiency and skills in academic writing, but holding learner agency (Ouyang & Jiao, 2021 ) can be more complex and challenging for younger learners. Further research is needed to understand students with varied domain knowledge, expertise, and writing abilities (Yan, 2023 ) and uncover individual differences in AI-assisted writing. Additionally, the participants in this study utilized GPT 3.5 for their AI-assisted writing practices. Given the rapid advancement of AI technologies, new AI models and applications are continuously emerging. Thus, future research should investigate how various AI models and functionalities might differently influence students, taking into account the ongoing developments and innovations in AI.

Data Availability

The data are available from the author upon reasonable request.

Abdel Latif, M. M. A. (2021). Remodeling writers’ composing processes: Implications for writing assessment. Assessing Writing, 50 , 100547. https://doi.org/10.1016/j.asw.2021.100547

Article   Google Scholar  

Almusharraf, N., & Alotaibi, H. (2023). An error-analysis study from an EFL writing context: Human and automated essay scoring approaches. Technology, Knowledge and Learning, 28 (3), 1015–1031. https://doi.org/10.1007/s10758-022-09592-z

American Psychological Association. (2020).  Publication manual of the American Psychological Association  (7th ed.).

Atkinson, D. (2003). L2 writing in the post-process era: Introduction. Journal of Second Language Writing, 12 (1), 3–15. https://doi.org/10.1016/S1060-3743(02)00123-6

Bahari, A. (2021). Computer-mediated feedback for L2 learners: Challenges versus affordances. Journal of Computer Assisted Learning, 37 (1), 24–38. https://doi.org/10.1111/jcal.12481

Barrot, J. S. (2023a). Using ChatGPT for second language writing: Pitfalls and potentials. Assessing Writing, 57 , 100745. https://doi.org/10.1016/j.asw.2023.100745

Barrot, J. S. (2023b). Using automated written corrective feedback in the writing classrooms: Effects on L2 writing accuracy. Computer Assisted Language Learning, 36 (4), 584–607.

Barrot, J. S. (2023c). ChatGPT as a language learning tool: An emerging technology report. Technology, Knowledge and Learning. https://doi.org/10.1007/s10758-023-09711-4

Bedington, A., Halcomb, E. F., McKee, H. A., Sargent, T., & Smith, A. (2024). Writing with generative AI and human-machine teaming: Insights and recommendations from faculty and students. Computers and Composition, 71 , 102833. https://doi.org/10.1016/j.compcom.2024.102833

Cancino, M., & Panes, J. (2021). The impact of google translate on L2 writing quality measures: Evidence from chilean EFL high school learners. System, 98 , 102464. https://doi.org/10.1016/j.system.2021.102464

Cao, L., & Dede, C. (2023). Navigating a world of generative AI: Suggestions for educators . The next level lab at harvard graduate school of education. President and Fellows of Harvard College: Cambridge, MA.

Chan, C., & Hu, W. (2023). Students’ voices on generative AI: Perceptions, benefits, and challenges in higher education. International Journal of Educational Technology in Higher Education . https://doi.org/10.1186/s41239-023-00411-8

Creswell, J. W. (2017). Qualitative inquiry and research design: Choosing among the five traditions . Sage.

Google Scholar  

Dixon-Román, E., Nichols, T. P., & Nyame-Mensah, A. (2020). The racializing forces of/in AI educational technologies. Learning, Media and Technology, 45 (3), 236–250. https://doi.org/10.1080/17439884.2020.1667825

Eaton, S. (2023). Six tenets of postplagiarism: Writing in the age of artificial intelligence. University of Calgary. http://hdl.handle.net/1880/115882 .

Ebadi, S., & Amini, A. (2022). Examining the roles of social presence and human-likeness on Iranian EFL learners’ motivation using artificial intelligence technology: A case of CSIEC chatbot. Interactive Learning Environments, 32 (2), 1–19. https://doi.org/10.1080/10494820.2022.2096638

Fariani, R. I., Junus, K., & Santoso, H. B. (2023). A systematic literature review on personalised learning in the higher education context. Technology, Knowledge and Learning, 28 (2), 449–476. https://doi.org/10.1007/s10758-022-09628-4

Ferrara, A. (1998). Reflective authenticity . Routledge.

Flower, L., & Hayes, J. R. (1981). A cognitive process theory of writing. College Composition & Communication, 32 (4), 365–387.

Fryer, L. K., & Carpenter, R. (2006). Bots as language learning tools. Language Learning & Technology, 10 , 8–14.

Gayed, J. M., Carlon, M. K. J., Oriola, A. M., & Cross, J. S. (2022). Exploring an AI-based writing Assistant’s impact on English language learners. Computers and Education: Artificial Intelligence, 3 , 100055. https://doi.org/10.1016/j.caeai.2022.100055

Glaser, N. (2023). Exploring the potential of ChatGPT as an educational technology: An emerging technology report. Technology, Knowledge and Learning, 28 (4), 1945–1952. https://doi.org/10.1007/s10758-023-09684-4

Golob, U. (2018). Sense-making. In R. L. Heath, W. Johansen, J. Falkheimer, K. Hallahan, J. J. C. Raupp, & B. Steyn (Eds.), The international encyclopedia of strategic communication (pp. 1–9). Wiley.

Graham, S. S. (2023). Post-process but not post-writing: large language models and a future for composition pedagogy. Composition Studies, 51 (1), 162–218.

Guo, K., Wang, J., & Chu, S. K. W. (2022). Using chatbots to scaffold EFL students’ argumentative writing. Assessing Writing, 54 , 100666. https://doi.org/10.1016/j.asw.2022.100666

Han, J., Yoo, H., Kim, Y., Myung, J., Kim, M., Lim, H., Kim, J., Lee, T., Hong, H., Ahn, S., & Oh, A. (2023). RECIPE: How to Integrate ChatGPT into EFL writing education. arXiv:2305.11583 . https://doi.org/10.48550/arXiv.2305.11583

Hayes, J. R. (2012). Modeling and remodeling writing. Written Communication, 29 (3), 369–388. https://doi.org/10.1177/0741088312451260

Heidegger, M. (1962). Being and time (J. Macquarrie & E. Robinson, Trans.). New York: Harper & Row (Original work published 1927).

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial intelligence in education: Promises and implications for teaching and learning . Center for Curriculum Redesign.

Huang, W., Hew, K., & Fryer, L. (2022). Chatbots for language learning—Are they really useful? A systematic review of chatbot-supported language learning. Journal of Computer Assisted Learning, 38 (1), 237–257.

Hwang, G. J., Xie, H., Wah, B. W., & Gašević, D. (2020). Vision, challenges, roles and research issues of Artificial Intelligence in Education. Computers & Education: Artificial Intelligence, 1 , Article 100001. https://doi.org/10.1016/j.caeai.2020.100001

Jabotinsky, H. Y., & Sarel, R. (2022). Co-authoring with an AI? Ethical dilemmas and artificial intelligence. SSRN Scholarly Paper . https://doi.org/10.2139/ssrn.4303959

Jeon, J. (2021). Chatbot-assisted dynamic assessment (CA-DA) for L2 vocabulary learning and diagnosis. Computer Assisted Language Learning, 36 (7), 1–27. https://doi.org/10.1080/09588221.2021.1987272

Johnson, M. D. (2017). Cognitive task complexity and L2 written syntactic complexity, accuracy, lexical complexity, and fluency: A research synthesis and meta-analysis. Journal of Second Language Writing, 37 , 13–38. https://doi.org/10.1016/j.jslw.2017.06.001

Johnson, G. P. (2023). Don’t act like you forgot: Approaching another literacy “crisis” by (re)considering what we know about teaching writing with and through technologies. Composition Studies, 51 (1), 169–175.

Kang, J., & Yi, Y. (2023). Beyond ChatGPT: Multimodal generative AI for L2 writers. Journal of Second Language Writing, 62 , 101070. https://doi.org/10.1016/j.jslw.2023.101070

Kellogg, R. T. (1996). A model of working memory in writing. In C. M. Levy & S. Ransdell (Eds.), The science of writing: Theories, methods, individual differences and applications (pp. 57–71). Laurence Erlbaum Associates.

Khuder, B., & Harwood, N. (2015). Writing in test and non-test situations: Process and product. Journal of Writing Research, 6 (3), 233–278.

Klein, G., Moon, B., & Hoffman, R. R. (2006). Making sense of sensemaking: A macrocognitive model. IEEE Intelligent Systems, 21 (5), 88–92.

Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). Exploring generative artificial intelligence preparedness among university language instructors: A case study. Computers and Education: Artificial Intelligence, 5 , 100156. https://doi.org/10.1016/j.caeai.2023.100156

Koltovskaia, S. (2020). Student engagement with automated written corrective feedback (AWCF) provided by Grammarly: A multiple case study. Assessing Writing, 44 , 100450.

Kruse, O., Rapp, C., Anson, C., Benetos, K., Cotos, E., Devitt, A., & Shibani, A. (Eds.). (2023). Digital writing technologies in higher education . Springer.

Lapadat, J. C. (2012). Thematic analysis. In A. J. Mills, G. Durepos, & E. Weibe (Eds.), The encyclopedia of case study research (pp. 926–927). Sage.

Li, B., Wang, C., Bonk, C., & Kou, X. (2024). Exploring inventions in self-directed language learning with generative AI: Implementations and perspectives of YouTube content creators. TechTrends . https://doi.org/10.1007/s11528-024-00960-3

Lin, M. P. C., & Chang, D. (2020). Enhancing post-secondary writers’ writing skills with a chatbot: A mixed-method classroom study. Journal of Educational Technology & Society, 23 (1), 78–92.

Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry . Sage.

Book   Google Scholar  

Link, S., Mehrzad, M., & Rahimi, M. (2022). Impact of automated writing evaluation on teacher feedback, student revision, and writing improvement. Computer Assisted Language Learning, 35 (4), 605–634. https://doi.org/10.1080/09588221.2020.1743323

Memarian, B., & Doleck, T. (2023). Fairness, accountability, transparency, and ethics (FATE) in artificial intelligence (AI), and higher education: A systematic review. Computers and Education: Artificial Intelligence. https://doi.org/10.1016/j.caeai.2023.100152

Mohsen, M. A. (2021). L1 versus L2 writing processes: What insight can we obtain from a keystroke logging program? Language Teaching Research, 4 , 48–62. https://doi.org/10.1177/13621688211041292

Moran, D. (2002). Introduction to phenomenology . Routledge.

Ng, D., Leung, J., Chu, S., & Qiao, M. (2021). Conceptualizing AI literacy: An exploratory review. Computers and Education: Artificial Intelligence, 2 , 100041. https://doi.org/10.1016/j.caeai.2021.100041

Ouyang, F., & Jiao, P. (2021). Artificial intelligence in education: The three paradigms. Computers and Education: Artificial Intelligence, 2 , 100020. https://doi.org/10.1016/j.caeai.2021.100020

Pandarova, I., Schmidt, T., Hartig, J., Boubekki, A., Jones, R. D., & Brefeld, U. (2019). Predicting the difficulty of exercise items for dynamic difficulty adaptation in adaptive language tutoring. International Journal of Artificial Intelligence in Education, 29 (3), 342–367. https://doi.org/10.1007/s40593-019-00180-4

Poquet, O. (2024). A shared lens around sensemaking in learning analytics: What activity theory, definition of a situation and affordances can offer. British Journal of Educational Technology . https://doi.org/10.1111/bjet.13435

Prince, R., & Archer, A. (2014). Exploring voice in multimodal quantitative texts. Literacy & Numeracy Studies, 22 (1), 39–57. https://doi.org/10.5130/lns.v22i1.4178

Ranalli, J. (2021). L2 student engagement with automated feedback on writing: Potential for learning and issues of trust. Journal of Second Language Writing, 52 , 100816. https://doi.org/10.1016/j.jslw.2021.100816

Rings, M. (2017). Authenticity, self-fulfillment, and self-acknowledgment. The Journal of Value Inquiry, 51 (3), 475–489.

Saldaña, J. (2016). The coding manual for qualitative researchers (3rd ed.). Sage.

Sanchez-Martin, C., Hirsu, L., Gonzales, L., & Alvarez, S. P. (2019). Pedagogies of digital composing through a translingual approach. Computers and Composition, 52 , 142–157. https://doi.org/10.1016/j.compcom.2019.02.007

Schulze, M. (2008). AI in CALL: Artificially inflated or almost imminent? CALICO Journal, 25 (3), 510–527. https://doi.org/10.1558/cj.v25i3.510-527

Shi, H., & Aryadoust, V. (2023). A systematic review of automated writing evaluation systems. Education and Information Technologies, 28 (1), 771–795. https://doi.org/10.1007/s10639-022-11200-7

Smith, J. A. (1996). Beyond the divide between cognition and discourse: Using interpretative phenomenological analysis in health psychology. Psychology and Health, 11 (2), 261–271. https://doi.org/10.1080/08870449608400256

Smith, J. A., Flower, P., & Larkin, M. (2009). Interpretative phenomenological analysis: Theory, method and research . Sage.

Smith, J. A., & Shinebourne, P. (2012). Interpretative phenomenological analysis. In H. Cooper, P. M. Camic, D. L. Long, A. T. Panter, D. Rindskopf, & K. J. Sher. (Eds.), Research designs: Quantitative, qualitative, neuropsychological, and biological (pp. 73–82). American Psychological Association. https://doi.org/10.1037/13620-005 .

Southworth, J., Migliaccio, K., Glover, J., Reed, D., McCarty, C., Brendemuhl, J., & Thomas, A. (2023). Developing a model for AI Across the curriculum: Transforming the higher education landscape via innovation in AI literacy. Computers and Education: Artificial Intelligence, 4 , 100127. https://doi.org/10.1016/j.caeai.2023.100127

Steiss, J., Tate, T. P., Graham, S., Cruz, J., Hebert, M., Wang, J., Moon, Y., Tseng, W., Warschauer, M., & Olson, C. (2024). Comparing the quality of human and ChatGPT feedback on students’ writing. Learning and Instruction . https://doi.org/10.1016/j.learninstruc.2024.101894

Su, Y., Lin, Y., & Lai, C. (2023). Collaborating with ChatGPT in argumentative writing classrooms. Assessing Writing, 57 , 100752. https://doi.org/10.1016/j.asw.2023.100752

Tan, X., Xu, W., & Wang, C. (2024). Purposeful remixing with generative AI: Constructing designer voice in multimodal composing. arXiv preprint arXiv:2403.19095.

Tsai, S. C. (2019). Using google translate in EFL drafts: A preliminary investigation. Computer Assisted Language Learning, 32 (5–6), 510–526. https://doi.org/10.1080/09588221.2018.1527361

Tseng, W., & Warschauer, M. (2023). AI-writing tools in education: If you can’t beat them, join them. Journal of China Computer-Assisted Language Learning, 3 (2), 258–262. https://doi.org/10.1515/jccall-2023-0008

Vetter, M. A., Lucia, B., Jiang, J., & Othman, M. (2024). Towards a framework for local interrogation of AI ethics: A case study on text generators, academic integrity, and composing with ChatGPT. Computers and Composition, 71 , 102831. https://doi.org/10.1016/j.compcom.2024.102831

Wang, C., Samuelson, B., & Silvester, K. (2020). Zhai nan, mai meng and filial piety: The translingual creativity of Chinese university students in an academic writing course. Journal of Global Literacies, Technologies, and Emerging Pedagogies, 6 (2), 1120–1143.

Warner, B. (2022). AI for Language Learning: ChatGPT and the Future of ELT . TESOL. http://blog.tesol.org/ai-for-language-learning-chatgpt-and-the-future-of-elt/?utm_content=buffer7d9a4&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer .

Weick, K. E., Sutcliffe, K. M., & Obstfeld, D. (2005). Organizing and the process of sensemaking. Organization Science, 16 (4), 409–421.

Yan, D. (2023). Impact of ChatGPT on learners in a L2 writing practicum: An exploratory investigation. Education and Information Technologies, 28 , 1–25. https://doi.org/10.1007/s10639-023-11742-4

Yang, S. J., Ogata, H., Matsui, T., & Chen, N. S. (2021). Human-centered artificial intelligence in education: Seeing the invisible through the visible. Computers & Education: Artificial Intelligence, 2 , Article 100008. https://doi.org/10.1016/j.caeai.2021.100008

Zhai, X. (2022). ChatGPT user experience: Implications for education. SSRN Scholarly Paper . https://doi.org/10.2139/ssrn.4312418 .

Download references

The author acknowledges that the research did not receive any funding.

Author information

Authors and affiliations.

Colby College, Waterville, ME, USA

Chaoran Wang

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Chaoran Wang .

Ethics declarations

Conflict of interest.

The author confirms that there are no conflicts of interest.

Ethical Approval

The study is conducted with permission from and following the guidelines of the university’s Institutional Review Board.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Wang, C. Exploring Students’ Generative AI-Assisted Writing Processes: Perceptions and Experiences from Native and Nonnative English Speakers. Tech Know Learn (2024). https://doi.org/10.1007/s10758-024-09744-3

Download citation

Accepted : 14 May 2024

Published : 30 May 2024

DOI : https://doi.org/10.1007/s10758-024-09744-3

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial Intelligence
• Find a journal
• Publish with us
• Track your research

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• How to Write a Paper with ChatGPT | Tips & Examples

How to Write a Paper with ChatGPT | Tips & Examples

Published on 17 August 2023 by Koen Driessen .

A good research paper demonstrates your academic writing skills and knowledge of your chosen topic.

Your research paper should be based on in-depth independent research. However, generative AI tools like ChatGPT can be effectively used throughout the research process to:

• Brainstorm research questions
• Develop a methodology
• Create an outline
• Find sources
• Summarise and paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarising or paraphrasing text, receiving feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to help formulate research questions , brainstorm potential thesis statements , or narrow down a broad subject area to a specific topic that interests you.

However, make sure that the outputs make sense and meet the requirements of your assignment. You can adapt these outputs manually, or use further prompts to ensure they meet your needs. For more information, see our tips for creating effective ChatGPT prompts .

• Generate three possible research questions for a research paper on the following topic: “The role of virtual reality in enhancing training and skill development in various industries.”
• “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods across different industries?”
• “How does the level of immersion in virtual reality training impact knowledge retention and skill transfer in fields such as medicine, aviation, and manufacturing?”
• “What are the key factors that influence the successful integration and adoption of virtual reality technology for training purposes in diverse industries, and what challenges hinder its widespread implementation?”

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

Your paper should clearly indicate the data collection and analysis methods you used in your research.

You can use ChatGPT to help decide what kind of research you will conduct (e.g., qualitative or quantitative ), how you will analyse the data, and how you will mitigate potential research bias .

Bear in mind that you should be able to rationalize your chosen methodology . For example, you should ensure that it is either a standard methodology in the field or can be justified.

• Suggest three quantitative research methods appropriate to the following question: “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Experimental Study: Conduct a randomized controlled trial (RCT) where healthcare professionals are randomly assigned to either a virtual reality-based training group or a traditional training group. Both groups would receive training in specific healthcare tasks, and their cognitive and skill development outcomes would be measured and compared. Performance metrics, such as accuracy, speed, and efficiency, could be quantitatively assessed to determine the benefits of virtual reality-based training over traditional methods.
• Survey Research: Design a comprehensive survey targeting healthcare professionals who have undergone both virtual reality-based training and traditional training. The survey could include Likert-scale questions and structured response options to gauge their perceived cognitive and skill development benefits from each training method. Additionally, open-ended questions could be included to gather qualitative insights on specific strengths and weaknesses of each training approach.
• Task Performance Analysis: Implement a task-based assessment that simulates real-life healthcare scenarios, where participants are evaluated on their ability to handle critical situations. Participants would go through both virtual reality-based training and traditional training before being assessed in the simulated scenarios. Their performance in the assessment could be objectively measured using predefined criteria, allowing for a quantitative comparison of skill development between the two training methods.

A clear outline can help structure your paper, organise your arguments effectively, and make your research more efficient.

You can use generative AI tools like ChatGPT to formulate a potential outline to help guide your research. You can be as specific as you like, giving an overview of your research objectives , main arguments, and any evidence you intend to include in your paper.

However, ChatGPT outputs sometimes contain factual inaccuracies. It’s important to check the headings and subheadings suggested in the output and adapt them to meet your needs.

• Create an outline for an academic research paper with the following research question:“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?” The paper will be about 10 pages long.

B. Existing studies on cognitive and skill development benefits of virtual reality training

C. Comparison of virtual reality-based training with traditional training methods

D. Gaps in the literature and research limitations

III. Theoretical Framework

A. Theoretical basis for cognitive and skill development in training

B. Application of cognitive theories to virtual reality-based training

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

A. Research design and approach (e.g., quasi-experimental, pre-post intervention)

B. Selection of participants and sample size calculation

C. Description of the virtual reality-based training and traditional training programs

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

A. Presentation of the results of the cognitive and skill development assessments

B. Comparison of outcomes between virtual reality-based training and traditional training

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

A. Interpretation of findings in the context of the research question

B. Comparison of results with existing literature

C. Explanation of how virtual reality-based training impacts cognitive processes and skill development

D. Limitations of the study and areas for future research

VIII. Practical Implications

A. Practical applications of virtual reality-based training in healthcare settings

B. Recommendations for integrating virtual reality training in healthcare education

C. Benefits of virtual reality for continuous professional development in healthcare

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

C. Contributions of the study to the field of healthcare training

D. Concluding remarks

X. References

You can use ChatGPT to help find sources relevant to your research. However, it’s important to be aware of the limitations of ChatGPT (for example, it occasionally cites nonexistent sources).

Instead of asking ChatGPT for specific source recommendations, try asking it for recommendations on the types of sources relevant to your research topic. You can also use it to generate a list of relevant keywords to use in your literature search.

• What types of sources could I use to write a research paper on the following research question? “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Academic Journals: Peer-reviewed journals are valuable sources of scholarly research. Look for articles in medical education, cognitive psychology, virtual reality applications in healthcare, and technology-enhanced learning.
• Research Studies: Seek out published research studies that specifically investigate the impact of virtual reality-based training on cognitive and skill development in healthcare professionals.
• Systematic Reviews and Meta-Analyses: These studies provide comprehensive overviews of existing research on a specific topic, making them a valuable source for summarizing and analyzing the overall evidence.
• Books and Book Chapters: Academic books and book chapters authored by experts in the fields of medical education, virtual reality, cognitive science, or instructional design can provide in-depth insights and theoretical foundations.
• Conference Proceedings: Proceedings from relevant conferences and symposiums may present the latest findings and advancements in virtual reality-based training and healthcare education.
• Educational Institution Websites: Universities and medical schools often publish research papers, case studies, and whitepapers related to medical education and virtual reality training.
• Industry Reports: Reports and whitepapers from healthcare organizations or technology companies exploring the benefits of virtual reality-based training in the healthcare sector.
• Government and Non-profit Organisations: Look for reports and publications from government agencies and non-profit organisations that focus on medical education and healthcare training.
• Online Databases: Utilize academic databases such as PubMed, Google Scholar, IEEE Xplore, and ScienceDirect to search for peer-reviewed research articles and conference papers.
• Expert Interviews: If possible, conduct interviews with experts in medical education, cognitive science, and virtual reality to gain valuable insights and perspectives.
• Surveys and Polls: Refer to reputable surveys and polls related to virtual reality-based training in the healthcare industry for additional statistical data.

You can use ChatGPT to paraphrase or summarise text. This can help you to condense sources to their most important points and explore new ways of expressing your ideas.

Alternatively you can use the more specialised tools featured on Scribbr’s AI writing resources page, which are designed specifically for these purposes and will give a smoother user experience.

• Provide a short summary of the following text:“One of the most profound applications of VR in healthcare is its use in surgical training. Traditionally, surgical training has relied on a combination of didactic lectures, observation of procedures, and hands-on experience in the operating room. However, these methods may not provide the ideal environment for novices to develop the necessary dexterity and spatial understanding essential for complex surgeries. VR overcomes these limitations by offering immersive, true-to-life simulations that allow surgeons to navigate through intricate anatomical structures, practice incisions, and learn to manage unexpected challenges that may arise during surgeries. This hands-on experience in a risk-free environment not only enhances technical skills but also builds confidence and reduces the learning curve for new surgical techniques.”
• Virtual Reality (VR) has a profound impact on healthcare, particularly in surgical training, as it provides immersive simulations that help surgeons develop dexterity, spatial understanding, and confidence for complex surgeries in a risk-free environment, ultimately enhancing their technical skills and reducing the learning curve.

When you’ve finished writing your research paper, you can use ChatGPT to receive feedback. You can be as specific as you like, selecting particular aspects the output should focus on (e.g., tone, clarity of structure, appropriateness of evidence to support your arguments).

You can also use ChatGPT to check grammar, spelling, and punctuation. However, it’s not designed for this purpose and occasionally misses errors. We recommend using a more specialised tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, Scribbr’s proofreading and editing service .

• Feedback the above text with regard to appropriateness of evidence and coherence of structure.
• The research paper demonstrates a well-structured and coherent presentation of the cognitive and skill development benefits of VR-based surgical training. The introduction effectively sets the context and rationale, while the literature review incorporates relevant historical and empirical evidence. The theoretical framework strengthens the foundation for the analysis.The methodology section could provide more details on the research design and study selection criteria. However, the sections on cognitive and skill development benefits present compelling evidence, supported by appropriate sub-sections.The exploration of improved patient outcomes lacks concrete examples but effectively outlines potential benefits. The section on challenges and future directions raises relevant points, but suggestions for solutions could enhance practicality.Overall, the paper combines theoretical, empirical, and practical evidence, offering a well-rounded approach. It establishes the significance of VR-based surgical training and concludes with a concise summary of key findings.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarise text . This can help you understand complex information more easily, summarise the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summariser , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialised tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, having ChatGPT write your college essay can negatively impact your application in numerous ways. ChatGPT outputs are unoriginal and lack personal insight.

Furthermore, Passing off AI-generated text as your own work is considered academically dishonest . AI detectors may be used to detect this offense, and it’s highly unlikely that any university will accept you if you are caught submitting an AI-generated admission essay.

However, you can use ChatGPT to help write your college essay during the preparation and revision stages (e.g., for brainstorming ideas and generating feedback).

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Driessen, K. (2023, August 17). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved 3 June 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, ethical implications of chatgpt, still have questions.

Watch CBS News

Lawyers fined for filing bogus case law created by ChatGPT

June 23, 2023 / 11:44 AM EDT / AP

A federal judge on Thursday imposed $5,000 fines on two lawyers and a law firm in an unprecedented instance in which ChatGPT was blamed for their submission of fictitious legal research in an aviation injury claim.

Judge P. Kevin Castel said they acted in bad faith. But he credited their apologies and remedial steps taken in explaining why harsher sanctions were not necessary to ensure they or others won't again let artificial intelligence tools prompt them to produce fake legal history in their arguments.

"Technological advances are commonplace and there is nothing inherently improper about using a reliable artificial intelligence tool for assistance," Castel wrote. "But existing rules impose a gatekeeping role on attorneys to ensure the accuracy of their filings."

A Texas judge earlier this month ordered attorneys to attest that they would not use ChatGPT or other generative artificial intelligence technology to write legal briefs because the AI tool can invent facts.

The judge said the lawyers and their firm, Levidow, Levidow & Oberman, P.C., "abandoned their responsibilities when they submitted non-existent judicial opinions with fake quotes and citations created by the artificial intelligence tool ChatGPT, then continued to stand by the fake opinions after judicial orders called their existence into question."

• Texas judge bans filings solely created by AI after ChatGPT made up cases
• A lawyer used ChatGPT to prepare a court filing. It went horribly awry.

In a statement, the law firm said it would comply with Castel's order, but added: "We respectfully disagree with the finding that anyone at our firm acted in bad faith. We have already apologized to the Court and our client. We continue to believe that in the face of what even the Court acknowledged was an unprecedented situation, we made a good faith mistake in failing to believe that a piece of technology could be making up cases out of whole cloth."

The firm said it was considering whether to appeal.

Bogus cases

Castel said the bad faith resulted from the failures of the attorneys to respond properly to the judge and their legal adversaries when it was noticed that six legal cases listed to support their March 1 written arguments did not exist.

The judge cited "shifting and contradictory explanations" offered by attorney Steven A. Schwartz. He said attorney Peter LoDuca lied about being on vacation and was dishonest about confirming the truth of statements submitted to Castel.

At a hearing earlier this month, Schwartz said he used the artificial intelligence-powered chatbot to help him find legal precedents supporting a client's case against the Colombian airline Avianca for an injury incurred on a 2019 flight.

Microsoft has invested some $1 billion in OpenAI, the company behind ChatGPT.

The chatbot, which generates essay-like answers to prompts from users, suggested several cases involving aviation mishaps that Schwartz hadn't been able to find through usual methods used at his law firm. Several of those cases weren't real, misidentified judges or involved airlines that didn't exist.

The made-up decisions included cases titled Martinez v. Delta Air Lines, Zicherman v. Korean Air Lines and Varghese v. China Southern Airlines.

The judge said one of the fake decisions generated by the chatbot "have some traits that are superficially consistent with actual judicial decisions" but he said other portions contained "gibberish" and were "nonsensical."

In a separate written opinion, the judge tossed out the underlying aviation claim, saying the statute of limitations had expired.

Lawyers for Schwartz and LoDuca did not immediately respond to a request for comment.

More from CBS News

Short-term vs. long-term care insurance: Which option is right for you?

McDonald's loses EU trademark fight over "Big Mac"

Cucumbers linked to salmonella outbreak that has spread to 25 states

AI simulations of loved ones help some mourners cope with grief