In August 2023, WIRED published Amanda Hoover's article "Use of AI Is Seeping Into Academic Journals—and It's Proving Difficult to Detect." She discusses how peer-reviewed journals struggle with submissions potentially written or influenced by AI, without clear disclosure from authors. More recently, Popular Science's Mack Degeurin reported on the issue, citing 404Media's Emanuel Maibert who found 115 papers on Google Scholar containing the phrase "As of my last knowledge update," indicating ChatGPT usage.
To verify, Marydee Ojala conducted a similar search on March 27, 2024, limiting results to articles since 2023. The search yielded 167 results. Examining the first 50 titles, 30% were legitimate uses discussing ChatGPT. However, 70% relied on ChatGPT for factual information or as a writing assistant, raising concerns about authenticity and accuracy.
This infiltration of AI-generated content presents an opportunity for information literacy education. Librarians can teach the importance of source verification and distinguish between platforms like Google Scholar and curated databases such as IEEE Xplore. Despite the 167 articles being a small fraction of total publications, they highlight the need for vigilance.
Educating researchers about the proper use of generative AI and promoting best practices can combat growing distrust in science, ensuring the integrity of scholarly research.
This article was originally published by INFORTODAY and has been edited by Glodom.
