用实时搜索提升大模型医疗问答准确率
SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?
- 将复杂医问转为可搜查询，调用实时搜索获取最新医学信息
- 通过不确定度筛选，只选最相关、最有用的知识输入模型
- 特别适合需要最新临床细节的复杂医疗问题解答
大型语言模型在通用领域表现优异，但在需要专业医学知识的任务中常表现不佳。传统检索增强生成（RAG）依赖静态知识库，易过时或不完整，难以捕捉精细临床细节。本文提出SearchRAG框架，利用实时搜索引擎克服这一局限：通过合成查询生成将复杂医疗问题转化为适合搜索的查询形式，并采用基于不确定性的知识选择机制，筛选并融合最相关、最具信息量的医学内容到模型输入中。实验表明，该方法显著提升了医疗问答任务的准确性，尤其在需要详细且最新知识的复杂问题上效果突出。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown remarkable capabilities in general domains but often struggle with tasks requiring specialized knowledge. Conventional Retrieval-Augmented Generation (RAG) techniques typically retrieve external information from static knowledge bases, which can be outdated or incomplete, missing fine-grained clinical details essential for accurate medical question answering. In this work, we propose SearchRAG, a novel framework that overcomes these limitations by leveraging real-time search engines. Our method employs synthetic query generation to convert complex medical questions into search-engine-friendly queries and utilizes uncertainty-based knowledge selection to filter and incorporate the most relevant and informative medical knowledge into the LLM's input. Experimental results demonstrate that our method significantly improves response accuracy in medical question answering tasks, particularly for complex questions requiring detailed and up-to-date knowledge.
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。