arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.18044cs.LG
收藏

查询的几何结构:医疗问答领域检索增强生成中基于查询的创新方法

The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA

Verily Life Sciences(Verily 生物科技)

Eric Yang, Jonathan Amar, Jong Ha Lee, Bhawesh Kumar, Yugang Jia

AI总结:

针对医疗问答场景下大语言模型的准确性与可靠性需求,提出基于查询的检索增强生成框架QB-RAG,通过预对齐查询与筛选后的可回答问题库提升性能,经医疗数据集验证效果优于现有方法,可支撑可信数字健康应用构建。

摘要:

将大语言模型(LLMs)部署于医疗问答场景,需要稳健的方法来保障准确性与可靠性。本研究提出基于查询的检索增强生成框架(QB-RAG),该框架通过将用户查询与一个由医疗内容衍生、经人工整理的可回答问题数据库预先对齐,来优化医疗问答中的检索增强生成(RAG)系统。QB-RAG的核心组件是一个基于大语言模型的过滤机制,可确保数据库中仅纳入相关且可回答的问题,从而实现规模化的可靠参考查询生成。我们为QB-RAG提供了理论依据,对现有检索增强技术开展了对比分析,并提出了一个可泛化的综合评估框架,该框架从忠实度、相关性及准则遵循度三个维度,同时评估检索效果与生成回复的质量。我们在一个医疗数据集上开展的实证评估表明,QB-RAG的性能优于现有检索方法,凸显了其在构建可信的医疗问答数字健康应用方面的实用价值。

英文摘要:

Deploying Large Language Models (LLMs) for healthcare question answering requires robust methods to ensure accuracy and reliability. This work introduces Query-Based Retrieval Augmented Generation (QB-RAG), a framework for enhancing Retrieval-Augmented Generation (RAG) systems in healthcare question-answering by pre-aligning user queries with a database of curated, answerable questions derived from healthcare content. A key component of QB-RAG is an LLM-based filtering mechanism that ensures that only relevant and answerable questions are included in the database, enabling reliable reference query generation at scale. We provide theoretical motivation for QB-RAG, conduct a comparative analysis of existing retrieval enhancement techniques, and introduce a generalizable, comprehensive evaluation framework that assesses both the retrieval effectiveness and the quality of the generated response based on faithfulness, relevance, and adherence to the guideline. Our empirical evaluation on a healthcare data set demonstrates the superior performance of QB-RAG compared to existing retrieval methods, highlighting its practical value in building trustworthy digital health applications for health question-answering.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑