SearchRAG：搜尋引擎能否助力基於大型語言模型的醫療問答？

SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?

February 18, 2025

作者: Yucheng Shi, Tianze Yang, Canyu Chen, Quanzheng Li, Tianming Liu, Xiang Li, Ninghao Liu

cs.AI

摘要

大型語言模型（LLMs）在通用領域展現了卓越的能力，但在需要專業知識的任務上往往表現不佳。傳統的檢索增強生成（RAG）技術通常從靜態知識庫中檢索外部信息，這些信息可能過時或不完整，缺乏對準確醫療問答至關重要的細粒度臨床細節。在本研究中，我們提出了SearchRAG，這是一種新穎的框架，通過利用即時搜索引擎來克服這些限制。我們的方法採用合成查詢生成，將複雜的醫療問題轉換為適合搜索引擎的查詢，並利用基於不確定性的知識選擇來過濾並將最相關且信息豐富的醫療知識整合到LLM的輸入中。實驗結果表明，我們的方法顯著提高了醫療問答任務中的回答準確性，特別是在需要詳細和最新知識的複雜問題上。

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Generation (RAG) techniques typically retrieve external information from static knowledge bases, which can be outdated or incomplete, missing fine-grained clinical details essential for accurate medical question answering.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.