用大模型整合多源数据，让生物医学问答更准更可信。
BioMedSearch: A Multi-Source Biomedical Retrieval Framework Based on LLMs
- 拆解问题、提取关键词，构建任务图融合文献与数据库
- 在三个推理层级上准确率分别提升至91.9%、81.0%、73.4%
- 适合需要精准生物医学信息的科研人员和临床研究者
生物医学查询常需理解基因调控机制、疾病病理过程等专业知识，依赖对复杂生理过程的分析及多源信息的有效整合。尽管大语言模型在通用推理中表现良好，但其生成内容常缺乏科学严谨性，因无法访问权威生物数据库，频繁虚构蛋白质功能、相互作用和结构细节。为此，我们提出 BioMedSearch，一个基于大模型的多源生物医学信息检索框架。该方法通过子查询分解、关键词提取、任务图构建和多源信息过滤，集成文献检索、蛋白数据库与网络搜索，实现对复杂生物医学问题的高效精准回答。为评估问答准确性，我们构建了包含3,000个问题的多层级数据集 BioMedMCQs，涵盖机制识别、非邻接语义整合与时间因果推理三类推理层级。实验表明，BioMedSearch 在所有层级均显著优于基线模型：一级推理准确率从59.1%提升至91.9%，二级从47.0%升至81.0%，三级最挑战的场景下从36.3%提升至73.4%。代码与数据集已开源。
原文摘要 · Abstract (English)
Biomedical queries often rely on a deep understanding of specialized knowledge such as gene regulatory mechanisms and pathological processes of diseases. They require detailed analysis of complex physiological processes and effective integration of information from multiple data sources to support accurate retrieval and reasoning. Although large language models (LLMs) perform well in general reasoning tasks, their generated biomedical content often lacks scientific rigor due to the inability to access authoritative biomedical databases and frequently fabricates protein functions, interactions, and structural details that deviate from authentic information. Therefore, we present BioMedSearch, a multi-source biomedical information retrieval framework based on LLMs. The method integrates literature retrieval, protein database and web search access to support accurate and efficient handling of complex biomedical queries. Through sub-queries decomposition, keywords extraction, task graph construction, and multi-source information filtering, BioMedSearch generates high-quality question-answering results. To evaluate the accuracy of question answering, we constructed a multi-level dataset, BioMedMCQs, consisting of 3,000 questions. The dataset covers three levels of reasoning: mechanistic identification, non-adjacent semantic integration, and temporal causal reasoning, and is used to assess the performance of BioMedSearch and other methods on complex QA tasks. Experimental results demonstrate that BioMedSearch consistently improves accuracy over all baseline models across all levels. Specifically, at Level 1, the average accuracy increases from 59.1% to 91.9%; at Level 2, it rises from 47.0% to 81.0%; and at the most challenging Level 3, the average accuracy improves from 36.3% to 73.4%. The code and BioMedMCQs are available at: https://github.com/CyL-ucas/BioMed_Search
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。