Skip to main content
. 2023 May 19;15(5):e39238. doi: 10.7759/cureus.39238

Figure 1. Example of fabricated and inaccurate references in ChatGPT-3.5 generated output.

Figure 1

Chen et al. and Kwon et al. are fabricated references. The Telfer et al. reference has correctly listed authors, title, and journal, but the year, volume, page numbers, and PMID number are inaccurate. Ultimately, this output produced no references deemed authentic and accurate. ChatGPT: Chat Generative Pre-trained Transformer.