When philosophy professor Darren Hick came across another case of cheating in his classroom at Furman University last semester, he posted an update to his followers on social media: “Aaaaand, I’ve caught my second ChatGPT plagiarist.”
Friends and colleagues responded, some with wide-eyed emojis. Others expressed surprise.
“Only 2?! I’ve caught dozens,” said Timothy Main, a writing professor at Conestoga College in Canada. “We’re in full-on crisis mode.”
Practically overnight, ChatGPT and other artificial intelligence chatbots have become the go-to source for cheating in college.
Now, educators are rethinking how they’ll teach courses this fall from Writing 101 to computer science. Educators say they want to embrace the technology’s potential to teach and learn in new ways, but when it comes to assessing students, they see a need to “ChatGPT-proof” test questions and assignments.
For some instructors that means a return to paper exams, after years of digital-only tests. Some professors will be requiring students to show editing history and drafts to prove their thought process. Other instructors are less concerned. Some students have always found ways to cheat, they say, and this is just the latest option.
An explosion of AI-generated chatbots including ChatGPT, which launched in November, has raised new questions for academics dedicated to making sure that students not only can get the right answer, but also understand how to do the work. Educators say there is agreement at least on some of the most pressing challenges.
— Are AI detectors reliable? Not yet, says Stephanie Laggini Fiore, associate vice provost at Temple University. This summer, Fiore was part of a team at Temple that tested the detector used by Turnitin, a popular plagiarism detection service, and found it to be “incredibly inaccurate.” It worked best at confirming human work, she said, but was spotty in identifying chatbot-generated text and least reliable with hybrid work.
— Will students get falsely accused of using artificial intelligence platforms to cheat? Absolutely. In one case last semester, a Texas A&M professor wrongly accused an entire class of using ChatGPT on final assignments. Most of the class was subsequently exonerated.
— So, how can educators be certain if a student has used an AI-powered chatbot dishonestly? It’s nearly impossible unless a student confesses, as both of Hicks’ students did. Unlike old-school plagiarism where text matches the source it is lifted from, AI-generated text is unique each time.
In some cases, the cheating is obvious, says Main, the writing professor, who has had students turn in assignments that were clearly cut-and-paste jobs. “I had answers come in that said, ‘I am just an AI language model, I don’t have an opinion on that,’” he said.
In his first-year required writing class last semester, Main logged 57 academic integrity issues, an explosion of academic dishonesty compared to about eight cases in each of the two prior semesters. AI cheating accounted for about half of them.
This fall, Main and colleagues are overhauling the school’s required freshman writing course. Writing assignments will be more personalized to encourage students to write about their own experiences, opinions and perspectives. All assignments and the course syllabi will have strict rules forbidding the use of artificial intelligence.
College administrators have been encouraging instructors to make the ground rules clear.
Many institutions are leaving the decision to use chatbots or not in the classroom to instructors, said Hiroano Okahana, the head of the Education Futures Lab at the American Council on Education.
