Research Letter | GPT-3.5 and GPT-4 show low accuracy in citing journal articles
9 Aug, 2023 | 15:31h | UTCAccuracy of Chatbots in Citing Journal Articles – JAMA Network Open
Commentary on Twitter
21% of medical journal articles cited by GPT-4 were found to be fake; GPT-3.5 cited an estimated 98% fake articles. Narrower topics had more fake articles than broader topics. Despite its promise, ChatGPT is currently not a reliable source of medical data. https://t.co/DCTIkT1OkZ
— JAMA Network Open (@JAMANetworkOpen) August 9, 2023