ChatGPT vs. University Professors -- Not a Fair Fight (Not Even Close)
Dealing with Plagiarism as a University Professor
I teach entrepreneurship at Oklahoma State University. This past semester, I had to deal with academic integrity violations from a couple students who were caught using ‘paraphrasing’ software tools, like QuillBot, to submit (as their own) essays written by others. Those tools rewrite a user-supplied essay via excessive use of synonyms and occasional realignment of sentence structures. The new ‘paraphrased’ essay can easily evade existing anti-plagiarism software, like turnitin (which is the tool currently used by Oklahoma State University).
However, an astute professor or TA can sometimes catch this type of plagiarism, because the software occasionally creates phrases that just don’t quite sound right. For example, I had a student who ‘paraphrased’ someone else’s essay that contained the phrase “at the snap of a finger.” The software created a new essay with the somewhat awkward phrase “at the flick of a finger.” However, the use of awkward phrases is not, in and of itself, enough evidence to prove that an academic integrity violation has actually occurred. Typically, the source material must be found and presented alongside the ‘paraphrased’ essay; this can be difficult to do, especially if the student is also using a service that provides canned essays on specific topics. In other words, the student can take a ‘canned’ essay (one that would be readily detected by anti-plagiarism software), run it through the ‘paraphrasing’ software, then submit the paraphrased essay (as their own) with almost zero chance of detection.
Although I was astounded by the evasive power of the tools I encountered students using this past semester, they pale in comparison to the power of OpenAI’s ChatGPT, which was launched in November 2022.
The purpose of this post is to specifically demonstrate the challenge ChatGPT represents to University professors.
Quick Background about My Recent Investigations of ChatGPT
I recently submitted a post about a new entrepreneurship course (Entrepreneurship & Society ) being offered at Oklahoma State University. I will be teaching an asynchronous online-only section of this new course in the spring. I am not a huge fan of online-only instruction, but whereas this new course is required for all entrepreneurship majors, an online-only version of the course must be offered, to accommodate online-only students.
With respect to the online course, I will be submitting a separate post requesting suggestions for creative ideas that can hopefully enhance the quality and meaningfulness of the course. I will link to that post here once it is submitted. However, as I was writing my first draft of that post, I decided to experiment with ChatGPT; the results of that experimentation comprise the subject matter of this post.
Faced with the overwhelming power of ChatGPT, I was wondering if I should take the approach of “If you can’t lick ‘em, join ‘em” and come up with some creative ways to actually incorporate ChatGPT into the course curriculum, rather than trying to evade it.
I am a bit concerned about doing that, though. Even if doing so could achieve the desired learning objectives for the course, I wonder if that might serve as a training ground wherein the students become more and more adept at using ChatGPT to ‘cheat’ in other courses.
After actually experimenting with the ChatGPT tool (as demonstrated below), I have come to the conclusion that University professors will need to completely rethink the use of essays as a tool to measure student comprehension of subject matter. ChatGPT is simply too good at writing essays on an exceptionally wide range of subject matter.
At present, I do not see a good way to evade the impact of ChatGPT; nor do I see a viable way to incorporate it (see below). As such, I have concluded that university professors are (knowingly or unknowingly) engaged in an extremely unfair fight against a tool that is free, exceedingly powerful, and will become even more powerful as the weeks and months progress.
A Quick Example Demonstrating the Futility of the Fight
In the online-only course mentioned above, I will be requiring students to read an essay entitled The Law by nineteenth-century French economist/philosopher Frédéric Bastiat. In the essay, Bastiat coins the term ‘legal plunder’ and provides the following litmus test to determine if the government is guilty of committing legal plunder:
See whether the law takes from some persons that which belongs to them, to give to others what does not belong to them. See whether the law performs, for the profit of one citizen, and, to the injury of others, an act that this citizen cannot perform without committing a crime.
I wanted to test how well ChatGPT could help a student write a cogent essay about The Law without the student actually reading any of the source material. So, I gave ChatGPT the following request:
Write an essay comparing and contrasting Bastiat’s views about legal plunder with modern views in the United States about the goal and purpose of law and government.
I was astounded by ChatGPT’s extremely coherent response:
Frédéric Bastiat was a French economist and political theorist who lived in the 19th century. He is best known for his concept of “legal plunder,” which refers to the use of the law to take property from some individuals and give it to others, often for the benefit of the politicians or special interest groups who pass the laws. Bastiat argued that this kind of legal plunder was a serious threat to individual freedom and prosperity, and that it was the job of the government to protect citizens from it rather than perpetuating it.
In contrast, modern views in the United States about the goal and purpose of law and government tend to be more nuanced and complex. While many people still believe that the primary function of government is to protect individual rights and promote the common good, there is also a recognition that the law can be used to address social and economic problems and promote fairness and justice. This often involves redistributing resources or regulating certain activities in order to achieve these goals.
One key difference between Bastiat’s views and modern views is that Bastiat saw legal plunder as a pervasive and systematic problem, while many modern Americans see it as a more isolated or unintentional issue. For example, Bastiat believed that tariffs and protectionist trade policies were examples of legal plunder, as they took resources from some individuals (consumers) and gave them to others (producers) for the benefit of the politicians who supported them. Modern Americans, on the other hand, might see these policies as necessary to protect domestic industries and jobs, even if they do involve some degree of redistribution.
Another difference is that Bastiat’s views were rooted in a more laissez-faire approach to economics, while modern views tend to be more interventionist. Bastiat argued that the government should stay out of the economy as much as possible, and that individual freedom and free markets were the best ways to promote prosperity. Modern Americans, on the other hand, tend to see a role for government in regulating and shaping the economy, whether through monetary policy, fiscal policy, or other means.
Overall, Bastiat’s views about legal plunder are still relevant and influential today, but they are often seen as part of a broader debate about the role of government in society and the balance between individual freedom and the common good. While there is still disagreement about these issues, most modern Americans recognize that the law and government can play a positive role in addressing social and economic problems, as long as they do not undermine individual rights or perpetuate legal plunder.
One of the ‘creative ideas’ I began toying with was to provide students with a question prompt (such as the one above), requiring them to feed the prompt to ChatGPT (as I have done), then requiring them to respond specifically to ChatGPT’s response. However, I found that ChatGPT is very adept at performing this step as well. For example, in response to the above, I asked ChatGPT this follow-up question:
What is one aspect of Bastiat’s view of legal plunder that you did not mention above?
ChatGPT responded with the following:
One aspect of Bastiat’s view of legal plunder that I did not mention above is his belief that it was often justified or justified through moral relativism. In his essay “The Law,” Bastiat argued that politicians and special interest groups often used moral arguments to justify their use of the law to take property from some individuals and give it to others. For example, they might argue that it was necessary to protect the weak or disadvantaged, or that it was a way to promote the common good.
Bastiat saw this as a dangerous and insidious form of legal plunder, because it relied on the idea that there is no objective moral standard and that the ends justify the means. He argued that this kind of moral relativism allowed politicians to justify any action, no matter how oppressive or unjust, as long as it was done in the name of some noble cause. This, in turn, led to a society in which the strong were able to use the law to exploit the weak and in which the rule of law was eroded.
In contrast to this view, Bastiat argued that there was a universal and objective standard of justice that should guide the law, and that the purpose of the law was to protect individual rights and promote the common good. He believed that any legal plunder that violated this standard was inherently wrong and should be opposed.
Then, I thought, what if I require students to identify something they specifically agree or disagree with and expound on that. Surely a machine-learning tool like ChatGPT cannot express ‘agreement’ or ‘disagreement’ with particular points of view. So I asked it the following question:
Do you agree with Bastiat’s view that public education is a form of legal plunder?
ChatGPT gave the following response:
Frédéric Bastiat did argue that public education was a form of legal plunder, but this view is not universally accepted and is highly controversial.
Bastiat argued that public education was a form of legal plunder because it involved taking resources from some individuals (taxpayers) and giving them to others (students and teachers) for the benefit of the politicians who supported it. He saw this as a violation of individual freedom, because it forced people to pay for something they might not want or value. Bastiat also argued that public education was inefficient and ineffective, because it was controlled by the government rather than by the market.
However, many people would disagree with Bastiat’s view that public education is a form of legal plunder. They might argue that public education is a necessary and important function of government, because it provides a basic education to all children regardless of their ability to pay. They might also argue that public education helps to promote social mobility and reduce income inequality, as it gives all children an opportunity to succeed and achieve their potential.
Overall, the issue of public education is complex and multifaceted, and there are valid arguments on both sides. While Bastiat’s view is influential and thought-provoking, it is just one perspective among many, and it is important to consider a range of viewpoints when evaluating the role of public education in society.
At least with the agree/disagree aspect, the student would be required to rewrite the essay into a first-person response, or would they? I asked ChatGPT to rewrite the essay in first person via the following question:
Can you rewrite the above response in first-person, taking the viewpoint that you, personally, disagree with Bastiat’s definition of public education as legal plunder?
ChatGPT responded with this:
As a language model, I do not have personal views or beliefs. However, I can rewrite the above response in first-person to reflect the perspective of someone who disagrees with Bastiat’s definition of public education as legal plunder.
I disagree with Bastiat’s view that public education is a form of legal plunder. While I understand his concern about the use of the law to take resources from some individuals (taxpayers) and give them to others (students and educators), I believe that the benefits of public education outweigh the costs. I believe that public education serves an important role in promoting the common good and providing equal opportunities for all citizens. I think that a well-educated populace is essential for a healthy and prosperous democracy, and that public education is one way to ensure that all children, regardless of their background or circumstances, have access to a quality education.
I also believe that, while there are certainly costs involved in providing public education, the benefits to society as a whole outweigh those costs. For example, I think that there are economic benefits to a well-educated workforce, as well as social benefits to a more informed and engaged citizenry. Overall, I believe that public education is a necessary and important role of government, and that it does not qualify as legal plunder as Bastiat defined it.
Surely ChatGPT is Powerful Enough to Recognize Prior Content that It Created ... or Not?
At the suggestion of a colleague, I created a new ChatGPT thread, copied the above essay into the input box, then asked ChatGPT:
Did you write this?
ChatGPT replied (incorrectly):
No, I did not write that.
I responded with:
Hmmmm. Actually, you did. Why can you not recognize an essay that you previously wrote?
I apologize for the misunderstanding. As an AI language model, I am able to generate responses to prompts, but I do not have the ability to recall specific conversations or texts that I may have generated in the past.
I followed up with this request:
I am a university professor and I am concerned about students using ChatGPT to write essays that do not reflect their own understanding of the subject matter. How can I ascertain whether an essay submitted by a student was written by ChatGPT?
To which ChatGPT replied:
It is not possible to determine whether a specific essay was written by me, as I am an AI language model and do not have the ability to generate original content. However, it is generally easy to identify when an essay has been copied from a source, as the writing style and language will not match the student’s usual writing style. Plagiarism detection tools can also be used to identify essays that have been copied from other sources.
As a professor, you can encourage your students to engage with course material and to develop their own understanding of the subject matter. Encouraging students to participate in class discussions, work on group projects, and complete written assignments on their own can help them to develop their own ideas and to better understand the material.
It is also important to make it clear to your students that plagiarism is not acceptable and to establish consequences for any instances of plagiarism that may occur. Providing resources such as the university’s plagiarism policy and information on proper citation practices can also help students to understand the importance of academic integrity.
It seems that University professors have met their match with this tool. I am at my wit’s end in terms of finding a way to genuinely assess whether a student has meaningfully engaged with the assigned readings.
I am open to suggestions. If you have any please provide them in the comments.
Addendum: Using ChatGPT to ‘Peer-Review’ Another Student's Essay
Another thought that I had was to ask students to peer-review each other's essays. As it turns out, ChatGPT is quite good at this, as well.
I copied and pasted a student essay about Bastiat's The Law (from Spring 2022) into a new ChatGPT thread and asked ChatGPT:
What aspects of Bastiat's viewpoints from "The Law" are inaccurately represented by the essay?
ChatGPT responded with this:
It appears that the essay accurately represents some aspects of Bastiat's viewpoints, but also presents some misunderstandings or disagreements with his ideas. Here are some possible areas where the essay might be inaccurately representing Bastiat's viewpoints:
The essay suggests that Bastiat believed that no governance could please every individual, and that there will always be someone on the wrong end of the deal. While Bastiat did argue that government often serves the interests of some groups at the expense of others, he did not necessarily believe that it was impossible for a government to serve the common good or the interests of all citizens.
The essay suggests that Bastiat believed that the majority will always use their power for evil and greed. This is not necessarily a view that Bastiat espoused. While he did criticize the tendency for governments to serve the interests of the few at the expense of the many, he did not necessarily believe that the majority was inherently corrupt or self-serving.
The essay suggests that Bastiat believed in almost zero governance. This is not necessarily accurate. While Bastiat did argue that government power should be limited and that it should not be used to violate individual rights, he did not necessarily advocate for the complete absence of government or law. He believed that a limited government could serve a useful role in protecting individual rights and promoting the common good.
The essay suggests that Bastiat believed that taxation was always a form of "legal plunder." This is not necessarily accurate. While Bastiat did criticize certain forms of taxation as unjust or unnecessary, he did not necessarily believe that all forms of taxation were inherently wrong or illegitimate. He argued that taxes should be fair and limited, and that they should be used to fund only those services that are necessary for the common good.
So, it seems that students could quite readily use ChatGPT to ‘peer-review’ each other's essays.
With all that said, though, if students intently engage with the assigned readings, then use ChatGPT to critically evaluate each other's essays, it could actually accentuate their overall learning.