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

Eric Yang, Jonathan Amar, Jong Ha Lee, Bhawesh Kumar, Yugang Jia
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

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 establish a theoretical foundation for QB-RAG, provide 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-yang25a, title = {The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare {QA}}, author = {Yang, Eric and Amar, Jonathan and Lee, Jong Ha and Kumar, Bhawesh and Jia, Yugang}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/yang25a/yang25a.pdf}, url = {https://proceedings.mlr.press/v298/yang25a.html}, abstract = {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 establish a theoretical foundation for QB-RAG, provide 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.} }
Endnote
%0 Conference Paper %T The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA %A Eric Yang %A Jonathan Amar %A Jong Ha Lee %A Bhawesh Kumar %A Yugang Jia %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-yang25a %I PMLR %U https://proceedings.mlr.press/v298/yang25a.html %V 298 %X 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 establish a theoretical foundation for QB-RAG, provide 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.
APA
Yang, E., Amar, J., Lee, J.H., Kumar, B. & Jia, Y.. (2025). The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/yang25a.html.

Related Material