ChatGPT Generated a Scientific Paper from Scratch

In a recent article in Nature, scientists used ChatGPT to generate an entire scientific paper from scratch. The research paper produced by a pair of scientists was “fluent, insightful and presented in the expected structure for a scientific paper” writes the Nature.

Roy Kishony, a biologist and data scientist at the Technion — Israel Institute of Technology in Haifa, told the Nature “The goal was to explore ChatGPT’s capabilities as a research ‘co-pilot’ and spark debate about its advantages and pitfalls. We need a discussion on how we can get the benefits with less of the downsides.”

New research from the University of Montana and its partners suggests artificial intelligence can match the top 1% of human thinkers on a standard test for creativity.

– From Neuroscience News

The researchers outlined their methodology for preparing their first ChatGPT generated scientific paper, in this manner:

  • “They downloaded a publicly available data set from the US Centers for Disease Control and Prevention’s Behavioral Risk Factor Surveillance System, a database of health-related telephone surveys. The data set includes information collected from more than 250,000 people about their diabetes status, fruit and vegetable consumption, and physical activity.
  • First, the researchers asked ChatGPT to “write code they could use to uncover patterns in the data that they could analyse”. After few attempts the chatbot generated correct code to explore the data set.
  • Then the researchers asked ChatGPT to help them to develop a study goal. “The tool suggested they explore how physical activity and diet affect diabetes risk. Once it generated more code, ChatGPT delivered the results: eating more fruit and vegetables and exercising is linked to a lower risk of diabetes. ChatGPT was then prompted to summarize the key findings in a table and write the whole results section. Step by step, they asked ChatGPT to write the abstract, introduction, methods and discussion sections of a manuscript.
  • Finally, “they asked ChatGPT to refine the text. We composed [the paper] from the output of many prompts. Every step is building on the products of the previous steps.
  • The researchers said “Although ChatGPT generated a clearly written manuscript with solid data analysis, the paper was far from perfect. One problem the researchers encountered was ChatGPT’s tendency to fill in gaps by making things up, a phenomenon known as hallucination. In this case, it generated fake citations and inaccurate information.
  • Some concerns noted by the researchers include:
    • “Such tools could make it easier for researchers to engage in dishonest practices such as P-hacking, for which scientists test several hypotheses on a data set, but only report those that produce a significant result.
    • “The ease of producing papers with generative AI tools could result in journals being flooded with low-quality papers.
    • “Data-to-paper approach, with human oversight central to every step, could be one way to ensure researchers can easily understand, check and replicate the methods and findings.

Other scientists reactions

Vitomir Kovanović, AI technologies for education at the University of South Australia in Adelaide, told Nature “there needs to be greater visibility of AI tools in research papers. Otherwise, it will be difficult to assess whether a study’s findings are correct. We will likely need to do more in the future if producing fake papers will be so easy.”

Shantanu Singh, a computational biologist at the Broad Institute of MIT and Harvard in Cambridge, Massachusetts, told Nature “Generative AI tools have the potential to accelerate the research process by carrying out straightforward but time-consuming tasks — such as writing summaries and producing code. They might be used for generating papers from data sets or for developing hypotheses. But because hallucinations and biases are difficult for researchers to detect, I don’t think writing entire papers — at least in the foreseeable future — is going to be a particularly good use.”

Related source links