Opinion
Artificial Intelligence Opinion

Three Steps to Prevent ChatGPT Misuse

Original or AI? How teachers can prevent plagiarism
By Spencer Burrows — March 07, 2023 4 min read
Conceptual vector illustration of Women in AI examining a virtual apple.
  • Save to favorites
  • Print

The remarkable technology known as ChatGPT has recently taken social media and the chattering class by storm. By now, many have witnessed at least one incredible product created by the artificial intelligence bot, be it a technical paper on coffee bean cultivation or a song about earthquakes in the style of Taylor Swift.

However, many teachers quickly realized a downside to the amazing technology: students potentially using the app to plagiarize assignments. First remote learning, then hybrid learning, and now this?

Yet, there are steps teachers can take to prevent the misuse. First, it is important to understand what ChatGPT is and is not. ChatGPT is a word-prediction technology, not an independent wealth of knowledge. That means the program needs to make a connection between real subjects to generate a fair word prediction. The app can draft a reasonable sounding paragraph on the link between “Aristotle” and “democracy” but not on a “thing” and “democracy.”

See Also

Illustration of field of word bubbles with technological elements superimposed.
Vanessa Solis/EdWeek + iStock/Getty images

While ChatGPT is not necessarily producing lies (intentional untruths), it is very often producing baloney. How to prevent this plain nonsense from infiltrating schoolwork? It all comes down to how you phrase your assignment questions.

Here’s what I recommend:

1. Avoid identifying terms and instead use signpost terms.

As I mentioned, ChatGPT needs real terms to produce a decent sounding response. I currently teach high school U.S. history and assigned a reading that covered Thomas Jefferson, the Declaration of Independence, and the Revolutionary War. Had I phrased the assignment question as: “How did Thomas Jefferson write the Declaration of Independence?” The ChatGPT response is:

“Thomas Jefferson wrote the Declaration of Independence by drafting an outline of grievances against the British government and a call for the colonies to declare their independence. He then wrote a rough draft of the document that was edited and revised by Congress over a period of several weeks. Jefferson’s final draft of the document was officially released on July 4th, 1776.”

That is a fair sounding response from ChatGPT.

However, look at the answer when I phrased my question as, “How did the author on Page 4 write that document?” The ChatGPT response to this second question was:

“The author on page 4 wrote the document using a combination of formal and informal language. They used a structure that is clear and easy to read, while also making sure to include specific details and relevant facts related to their subject. The author incorporates both personal opinion and open-mindedness in their writing, while also relying on research and data to back up their points.”

You can see here that ChatGPT has no idea who the author is and produced a baloney response. Hence, I encourage teachers to frame your assignment with language that requires the students to go back to the text and find the answer, such as using specific page numbers or references.

2. Require text citations in the response.

After asking the students to return to the text to find the answer or produce the analysis, ask for text citations as well. This really sends ChatGPT on a fishing expedition.

I asked the app, “Write one paragraph explaining how the author on Page 4 helped win the war. Use at least two citations from the text.” The response:

“The author on page four describes how Joseph Pilsudski, the founder of modern Poland, had a major role in helping win the war. Pilsudski mobilized a Polish army and forced the Austrians to sign an armistice, formally ending their occupation of Poland in 1918 (pg.4). He also formed a multi-national Polish army and ‘fought shoulder to shoulder with his former enemies against the Bolshevik menace’ (pg.4), helping Greece, Romania and Czechoslovakia gain independence from the Bolsheviks. Without Pilsudski’s efforts, the war with the Bolsheviks would have been much more difficult and prolonged and the outcome of the war would have been far different.”

Complete nonsense. ChatGPT has no idea who the author is and even less idea what war we are referring to, so students cannot effectively plagiarize an assignment that requires citations.

3. Ask for a modern-day connection in the analysis.

ChatGPT is not nearly as adept at generalizing on new or developing situations. When the app is asked: “How is the Revolutionary War related to the crisis in Ukraine?” The response is:

“The Revolutionary War is not directly related to the crisis in Ukraine. However, certain parallels can be drawn between the motivations of the revolutionaries in the American Revolution and those initiating the revolution in Ukraine. In both cases, people have sought a more equitable distribution of political and economic power, a greater say in governance, and more freedom from external control.”

Again, boilerplate language. The app took “revolution” and generalized language that could have described the Russian Revolution, the Cuban Revolution, or most any revolution for that matter. Requiring students to apply the subject to current events, therefore, lowers the likelihood they will outsource their thinking to AI.

I hope these tips keep you afloat until spring break. Best of luck!

Events

This content is provided by our sponsor. It is not written by and does not necessarily reflect the views of Education Week's editorial staff.
Sponsor
Recruitment & Retention Webinar
Hiring, Retention, and Fill Rates: A Data-Driven Sub Strategy
Explore what keeps substitutes coming back and hear how one district rebuilt its substitute hiring process and improved its fill rate.
Content provided by Frontline Education
Early Childhood K-12 Essentials Forum Early Childhood Education: Building Essential Skills for Success
Join this free virtual event to examine the biggest challenges in supporting young children, from preschool through elementary school. 
This content is provided by our sponsor. It is not written by and does not necessarily reflect the views of Education Week's editorial staff.
Sponsor
Student Absenteeism Webinar
Attendance Isn't an Attendance Problem
Boost attendance by strengthening relationships, belonging, and support with practical strategies from Doug Fisher & Nancy Frey.
Content provided by Corwin

EdWeek Top School Jobs

Teacher Jobs
Search over ten thousand teaching jobs nationwide — elementary, middle, high school and more.
View Jobs
Principal Jobs
Find hundreds of jobs for principals, assistant principals, and other school leadership roles.
View Jobs
Administrator Jobs
Over a thousand district-level jobs: superintendents, directors, more.
View Jobs
Support Staff Jobs
Search thousands of jobs, from paraprofessionals to counselors and more.
View Jobs

Read Next

Artificial Intelligence LAUSD Adopts Moratorium on Student AI Use, Another Move to Limit Classroom Tech
The nation's second-largest district is pausing student use of generative artificial intelligence.
Howard Blume, Los Angeles Times
3 min read
A student uses Ed, a new district-developed Artificial Intelligence-assisted "learning acceleration web-based platform that will boost student success and revolutionize how K-12 education is tailored to meet individual needs," during the official launch event at Edward R. Roybal Learning Center in Los Angeles on March 20, 2024 .
A student uses Ed, the Los Angeles Unified School District's custom AI platform that later failed, during a launch event at Edward R. Roybal Learning Center in Los Angeles on March 20, 2024. LAUSD has now adopted a moratorium on student AI use. New York City schools have banned AI-powered tools for elementary and middle school students, meaning the nation's two largest districts have adopted major restrictions on student AI use.
Christina House/Los Angeles Times/TNS
Artificial Intelligence New York, Los Angeles Restrict Student AI Use. Will Other Districts Follow?
The restrictions come amid rising concerns about overreliance on technology in schools.
7 min read
Mayor Zohran Kwame Mamdani and Schools Chancellor Kamar H. Samuels today announced a moratorium on student-facing generative Artificial Intelligence (AI) use in schools, alongside a new screen time policy, a decision that will impact nearly 600,000 public school students, or two-thirds of the system's total enrollment at The Brooklyn Steam Center in New York City on Sept. 2, 2026.
Mayor Zohran Kwame Mamdani and Schools Chancellor Kamar H. Samuels announced a moratorium on student-facing generative artificial intelligence use in schools and a new screen-time policy during a press conference at The Brooklyn Steam Center in New York City on Sept. 2, 2026. The moratorium is part of a growing nationwide movement to ban or limit the use of AI and decrease screen time in schools.
Katie Godowski/MediaPunch /IPX via AP
Artificial Intelligence Spotlight Spotlight on Using AI with Purpose: Building Responsible Practices for Schools
Learn how to implement AI responsibly with practical guidance for school leaders, teachers, and district decisionmakers.
Artificial Intelligence Schools Caught Flat-Footed After Google Makes Gemini Chatbot Available to All Students
Schools wrestle with the question of whether to permit or prohibit access to the AI chatbot.
5 min read
Social Studies teacher Simon Sharick supervises students at the Plymouth High School in Ohio on how to properly prompt the Gemini Ai App to get their desired information. Students were using the Gemini App for the first time on Friday, Aug. 28, 2026.
Students in a social studies class on Aug. 28, 2026, at Plymouth High School in Plymouth, Ohio, learn how to properly prompt Google's Gemini chatbot to generate useful and accurate information. In August, Google made Gemini available to K-12 students of all ages. <br/>
Ruddy Roye for Education Week