Saved in:
Bibliographic Details
Main Authors: Yang, Eric, Amar, Jonathan, Lee, Jong Ha, Kumar, Bhawesh, Jia, Yugang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.18044
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915417255051264
author Yang, Eric
Amar, Jonathan
Lee, Jong Ha
Kumar, Bhawesh
Jia, Yugang
author_facet Yang, Eric
Amar, Jonathan
Lee, Jong Ha
Kumar, Bhawesh
Jia, Yugang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18044
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA
Yang, Eric
Amar, Jonathan
Lee, Jong Ha
Kumar, Bhawesh
Jia, Yugang
Machine Learning
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.
title The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA
topic Machine Learning
url https://arxiv.org/abs/2407.18044