用知识图谱增强小模型，提升日语医学问答效果。
Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
- 构建基于知识图谱的检索增强生成框架，适配小型开源模型。
- 实验显示该方法对日语医学问答提升有限，依赖外部信息质量。
- 研究揭示低资源语言中RAG应用的关键挑战，适合医疗AI落地参考。
大型语言模型在医学问答中表现优异，但在日语场景下受限于隐私政策，难以使用GPT-4等商业模型。因此，近期研究转向指令微调的开源小型模型，但其与检索增强生成（RAG）结合的潜力尚未充分探索。本文首次针对小型开源模型，在日语医学问答中引入基于知识图谱（KG）的RAG框架。实验表明，该方法在小型模型上对日语医学问答的提升有限；案例分析进一步显示，RAG效果高度依赖外部检索内容的质量与相关性。这些发现为低资源语言中RAG的应用提供了重要启示，也为其他类似场景提供参考。
原文摘要 · Abstract (English)
Large language models (LLMs) perform well in medical QA, but their effectiveness in Japanese contexts is limited due to privacy constraints that prevent the use of commercial models like GPT-4 in clinical settings. As a result, recent efforts focus on instruction-tuning open-source LLMs, though the potential of combining them with retrieval-augmented generation (RAG) remains underexplored. To bridge this gap, we are the first to explore a knowledge graph-based (KG) RAG framework for Japanese medical QA small-scale open-source LLMs. Experimental results show that KG-based RAG has only a limited impact on Japanese medical QA using small-scale open-source LLMs. Further case studies reveal that the effectiveness of the RAG is sensitive to the quality and relevance of the external retrieved content. These findings offer valuable insights into the challenges and potential of applying RAG in Japanese medical QA, while also serving as a reference for other low-resource languages.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。