KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques

arXiv:2403.05881v1 Announce Type: new
Abstract: Large Language Models (LLMs) have significantly advanced healthcare innovation on generation capabilities. However, their application in real clinical settings is challenging due to potential deviations from medical facts and inherent biases. In this work, we develop an augmented LLM framework, KG-Rank, which leverages a medical knowledge graph (KG) with ranking and re-ranking techniques, aiming to improve free-text question-answering (QA) in the medical domain. Specifically, upon receiving a question, we initially retrieve triplets from a medical …

abstract advanced application arxiv biases capabilities clinical cs.cl facts framework graphs healthcare however innovation knowledge knowledge graphs language language models large language large language models llm llms medical ranking type work