用循证医学的元分析思想优化检索增强生成，提升医疗问答准确性
META-RAG: Meta-Analysis-Inspired Evidence-Re-Ranking Method for Retrieval-Augmented Generation in Evidence-Based Medicine
- 模仿元分析流程，融合可靠性、异质性等多维度评估证据质量
- 在PubMed数据集上使LLM诊断准确率提升最高达11.4%
- 适合需要高可信医疗推理的临床辅助系统开发者
循证医学（EBM）在临床应用中至关重要。医生通过查阅优质医学文献可有效降低误诊率。研究人员发现使用大语言模型（LLMs）的检索增强生成（RAG）技术处理EBM任务效率较高。然而，EBM对证据质量要求严格，现有RAG方法难以高效区分高质量证据。受循证医学中元分析启发，本文提出一种新的证据重排序与过滤方法，综合运用可靠性分析、异质性分析和外推性分析等多种EBM方法，模拟元分析过程，筛选最优证据供LLM用于诊断。实验表明，在PubMed数据集上，该方法可使诊断准确率最高提升11.4%。本方法成功提升了RAG从海量文献中提取高质量、高可靠性证据的能力，减少错误知识注入，帮助用户获得更有效的回复。
原文摘要 · Abstract (English)
Evidence-based medicine (EBM) holds a crucial role in clinical application. Given suitable medical articles, doctors effectively reduce the incidence of misdiagnoses. Researchers find it efficient to use large language models (LLMs) techniques like RAG for EBM tasks. However, the EBM maintains stringent requirements for evidence, and RAG applications in EBM struggle to efficiently distinguish high-quality evidence. Therefore, inspired by the meta-analysis used in EBM, we provide a new method to re-rank and filter the medical evidence. This method presents multiple principles to filter the best evidence for LLMs to diagnose. We employ a combination of several EBM methods to emulate the meta-analysis, which includes reliability analysis, heterogeneity analysis, and extrapolation analysis. These processes allow the users to retrieve the best medical evidence for the LLMs. Ultimately, we evaluate these high-quality articles and show an accuracy improvement of up to 11.4% in our experiments and results. Our method successfully enables RAG to extract higher-quality and more reliable evidence from the PubMed dataset. This work can reduce the infusion of incorrect knowledge into responses and help users receive more effective replies.
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。