Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation
This addresses the critical need for evidence-based and safe medical AI systems, particularly for handling private medical data, though it appears to be an incremental improvement over existing GraphRAG methods.
The paper tackles the problem of generating safe and reliable medical responses from Large Language Models by introducing MedGraphRAG, a graph-based Retrieval-Augmented Generation framework specifically designed for the medical domain. The results show that MedGraphRAG consistently outperforms state-of-the-art models across 9 medical Q&A benchmarks, 2 health fact-checking benchmarks, and one long-form generation dataset.
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.