It’s now well established that ChatGPT often makes up stuff — the official disclaimer on its site says “ChatGPT may produce inaccurate information about people, places, or facts”. But an economics professor has explained why the program does this.
David Smerdon, who’s an assistant professor at the University of Queensland, has a theory around how ChatGPT came up with the name and authors of an Economics Paper. When asked which was the most cited Economics Paper of all time, ChatGPT confidently replied with “A Theory of Economic History” by Douglass North and Robert Thomas, which was published in the Journal of Economic History in 1969. ChatGPT even came up with what the paper was about, and what its conclusions were.
It turns out that this paper was entirely made up — it didn’t exist. “ChatGPT is based on a language model, which assigns a probability distribution over sequences of words,” says Smerdon. “A rough way to think about it: Given the start of a sentence, it will try to guess the most likely words to come next. A simplistic example: Give it “An apple a day…” and it will scan its immense library and come up with the most likely continuation: “…keeps the doctor away.”” he says.
“ChatGPT is of course more sophisticated than that, and it also ‘predicts’ the start of sentences, and ensures that whole documents are consistent. But the fundamental idea of predicting the next words in a sequence is still the same. Now consider the prompt “What is the most cited economics paper of all time”. The most ‘likely’ beginning to a language-based answer to this question is “The most cited economics paper of all time is”, which is what chatGPT spits out,” he says. “No surprises there. But how does it choose the beginning of the title? It can’t scan papers themselves, but it can use website articles (inc. Wikipedia) that cite the titles of popular economics papers, and then use the words in the cited titles,” he adds.
“Throughout the last 70 years, the two most common words in the titles of highly-cited economics papers have been “economic” and “theory” (hat tip: Hugo M. Montesinos-Yufa and Brandon Brice, “The Era of Evidence”),” Smerdon says.
“So we get the stem “A Theory of Economic”. What comes next? The most probable word to finish this title consistently, given the pool of cited economics papers and the adjective ‘economic’, is “History”,” he continues.
“Now we have the title of our fake paper: “A Theory of Economic History”. We need the most probable author of this paper. The most highly-cited author associated with economic history is Nobel laureate Douglass North,” he says. “Douglass North has been cited over 120,000 times according to Google Scholar, and his most cited work, the book Structure and change in economic history, bears similarity to chatGPT’s title.”
“But wait – how many authors should our fake paper have? The most common number of authors in economics papers is 2. We need another author, and someone who best fits a co-author to Douglass North on a paper called “A Theory of Economic History”,” Smerdon adds.
“Douglass North had many co-authors, but his most cited work with a co-author was “The rise of the western world: A new economic history”, with Robert Thomas,” he continues.
“So Robert Thomas is our co-author. Finally, we need to choose a journal to publish our fake paper. Given the title and given the authors, which journal does chatGPT think is most likely?” asks Smerdon.
“Douglass North’s most-cited co-authored paper, “Constitutions and commitment: the evolution of institutions governing public choice in seventeenth-century England”, was published in The Journal of Economic History in 1989. But this isn’t the only reason! When associating an economics journal to go with this paper, chatGPT also draws on ALL of the references to a journal that contain either “Douglass North”, “Robert Thomas”, or “Economic History”. Douglass North became editor of The Journal of Economic History in 1960, and many website articles about the Nobel laureate reference this appointment. Combine this with his highly cited paper in 1989, and the choice is clear,” he goes on.
“And why 1969 as the publishing year? Here, the AI’s choice is not as clear. Douglass North published frequently in The Journal of Economic History from 1954-1992. He was the journal’s editor until 1966. The Nobel Committee cited his 1961 work as “Groundbreaking”, while his most cited work was in 1981,” he says.
“Why exactly chatGPT chose 1969 is unclear, but to a human, it is as plausible a choice as any – as is the fake paper!” he concludes.
It’s a pretty impressive bit of detective work, but indicates that while ChatGPT often seems very impressive to the regular user, it doesn’t always impress the experts in the fields it answers questions on. Most casual users wouldn’t have doubted ChatGPT’s convincing answer about the most cited economics paper of all time, but it couldn’t pass the scrutiny of an Economics Professor, who ended up working out how the computer program had come up with the answer that it did. While ChatGPT still comes up with some very detailed answers, this incident is a cautionary tale about how the program might just be hallucinating when it’s giving out what seems like very authoritative answers.
Pingback: Laywer In Trouble With Judge After ChatGPT Cited Made-Up Cases In Filing - MagicWand AI