发表机构
Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对医学MCQA中普通RAG降低LM性能的问题，提出MedJudgeRAG框架，将检索文档表示为动态知识图谱，为选项判断证据裁决并确定知识利用策略，经监督微调训练，实验证明其性能优于基线，且动态知识图谱在训练时作用更有效。
AI 中文摘要
在医学多项选择题问答（MCQA）中，检索增强生成（RAG）可补充语言模型（LMs）的领域知识。但普通RAG不加区分地使用检索到的文档，会降低LM性能。为此提出MedJudgeRAG框架，将检索文档表示为包含实体和关系的动态知识图谱。对每个选项，模型从检索文档和知识图谱判断证据裁决，基于裁决组合确定知识利用策略以推理出最终答案。通过教师LM生成的结构化推理痕迹进行监督微调训练，采用加权交叉熵损失对知识图谱和推理段进行差异化加权。在两个医学MCQA基准上的实验表明，MedJudgeRAG始终优于普通RAG和参数基线。消融分析显示，动态知识图谱在训练时作为图条件监督比在推理时作为显式输出更有效。代码和生成的推理痕迹可通过链接获取。
英文摘要
In medical multiple-choice question answering (MCQA), Retrieval-Augmented Generation (RAG) can supplement the domain knowledge of language models (LMs). However, since vanilla RAG indiscriminately utilizes retrieved documents, it can degrade LM performance. To address this, we propose MedJudgeRAG. Our framework represents retrieved documents as a dynamic knowledge graph (KG) composed of entities and relations. For each option, the model judges an evidence verdict from the retrieved documents and the KG. Based on the verdict combination, the model determines a knowledge utilization strategy to reason toward the final answer. These capabilities are trained via supervised fine-tuning using structured reasoning traces generated by a teacher LM. The training employs a weighted cross-entropy loss that differentially weights the KG and reasoning segments. Experiments on two medical MCQA benchmarks demonstrate that MedJudgeRAG consistently outperforms both vanilla RAG and parametric baselines. Furthermore, ablation analysis reveals that the dynamic KG is more effective as graph-conditioned supervision at training time than as an explicit output at inference time. Our code is available at https://github.com/hyu-amllab/medjudgerag, and the generated reasoning traces are released at https://huggingface.co/datasets/youarethewon/medjudgerag.
Comments16 pages, 2 figures, Accepted at The Workshop on Graph Foundation Models at the 43 rd International Conference on Machine Learning (ICML 2026)
