The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA
It addresses the need for trustworthy digital health applications in healthcare question-answering, though it appears incremental as it builds on existing RAG frameworks.
This paper tackles the problem of ensuring accuracy and reliability in healthcare question answering with LLMs by introducing Query-Based Retrieval Augmented Generation (QB-RAG), which pre-aligns user queries with a curated database of answerable questions, and demonstrates superior performance compared to existing retrieval methods in empirical evaluations.
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.