Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge

arXiv:2402.12352v1 Announce Type: new
Abstract: Large language models (LLMs) are transforming the way information is retrieved with vast amounts of knowledge being summarized and presented via natural language conversations. Yet, LLMs are prone to highlight the most frequently seen pieces of information from the training set and to neglect the rare ones. In the field of biomedical research, latest discoveries are key to academic and industrial actors and are obscured by the abundance of an ever-increasing literature corpus (the information …

abstract arxiv biomedical conversations cs.cl cs.ir graph graph-based highlight information knowledge language language models large language large language models llms natural natural language set training type vast via