RefAI: a GPT-powered retrieval-augmented generative tool for biomedical literature recommendation and summarization

Yiming Li, Jeff Zhao, Manqi Li, Yifang Dang, Evan Yu, Jianfu Li, Zenan Sun, Usama Hussein, Jianguo Wen, Ahmed M. Abdelhameed, Junhua Mai, Shenduo Li, Yue Yu, Xinyue Hu, Daowei Yang, Jingna Feng, Zehan Li, Jianping He, Wei Tao, Tiehang Duan et al. (3 additional authors not shown)

Abstract: Precise literature recommendation and summarization are crucial for biomedical professionals. While the latest iteration of generative pretrained transformer (GPT) incorporates 2 distinct modes—real-time search and pretrained model utilization—it encounters challenges in dealing with these tasks. Specifically, the real-time search can pinpoint some relevant articles but occasionally provides fabricated papers, whereas the pretrained model excels in generating well-structured summaries but struggles to cite specific sources. In response, this study introduces RefAI, an innovative retrieval-augmented generative tool designed to synergize the strengths of large language models (LLMs) while overcoming their limitations.