HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses

arXiv:2312.15883v2 Announce Type: replace
Abstract: In this paper, we investigate the retrieval-augmented generation (RAG) based on Knowledge Graphs (KGs) to improve the accuracy and reliability of Large Language Models (LLMs). Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. To this end, we develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework, which leverages LLMs' powerful reasoning capacity to compensate for the incompleteness of user queries, optimizes the interaction process with LLMs, …

abstract accuracy arxiv cs.ai cs.cl framework graph graphs hypothesis knowledge knowledge graph knowledge graphs language language models large language large language models llms medical paper parsing query rag reliability responses retrieval retrieval-augmented type