Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation

TL;DR

MedGraphRAG is a novel graph-based retrieval-augmented generation framework tailored for medical applications, enhancing the safety, reliability, and evidence-based response generation of large language models in healthcare.

Contribution

The paper introduces Triple Graph Construction and U-Retrieval techniques to improve medical LLMs with source credibility and comprehensive responses, addressing complexity and evidence generation issues.

Findings

Outperforms state-of-the-art models on 9 medical Q&A benchmarks

Ensures responses include credible sources and definitions

Validated on health fact-checking and long-form generation datasets

Abstract

We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model (LLM) capabilities for generating evidence-based medical responses, thereby improving safety and reliability when handling private medical data. Graph-based RAG (GraphRAG) leverages LLMs to organize RAG data into graphs, showing strong potential for gaining holistic insights from long-form documents. However, its standard implementation is overly complex for general use and lacks the ability to generate evidence-based responses, limiting its effectiveness in the medical field. To extend the capabilities of GraphRAG to the medical domain, we propose unique Triple Graph Construction and U-Retrieval techniques over it. In our graph construction, we create a triple-linked structure that connects user documents to credible medical sources and controlled vocabularies. In the retrieval process, we propose U-Retrieval which combines Top-down Precise Retrieval with Bottom-up Response Refinement to balance global context awareness with precise indexing. These effort enable both source information retrieval and comprehensive response generation. Our approach is validated on 9 medical Q\&A benchmarks, 2 health fact-checking benchmarks, and one collected dataset testing long-form generation. The results show that MedGraphRAG consistently outperforms state-of-the-art models across all benchmarks, while also ensuring that responses include credible source documentation and definitions. Our code is released at: https://github.com/MedicineToken/Medical-Graph-RAG.