Query pipeline optimization for cancer patient question answering systems

TL;DR

This paper introduces a three-aspect optimization framework for RAG query pipelines in cancer patient QA systems, enhancing retrieval and understanding using biomedical databases.

Contribution

It presents a novel domain-specific optimization approach with new retrieval and semantic techniques tailored for cancer-related question answering.

Findings

Optimized RAG improved answer accuracy by 5.24% over chain-of-thought prompting.

Hybrid Semantic Real-time Document Retrieval (HSRDR) outperformed existing document retrieval methods.

Semantic Enhanced Overlap Segmentation (SEOS) enhanced contextual understanding in biomedical QA.

Abstract

Retrieval-augmented generation (RAG) mitigates hallucination in Large Language Models (LLMs) by using query pipelines to retrieve relevant external information and grounding responses in retrieved knowledge. However, query pipeline optimization for cancer patient question-answering (CPQA) systems requires separately optimizing multiple components with domain-specific considerations. We propose a novel three-aspect optimization approach for the RAG query pipeline in CPQA systems, utilizing public biomedical databases like PubMed and PubMed Central. Our optimization includes: (1) document retrieval, utilizing a comparative analysis of NCBI resources and introducing Hybrid Semantic Real-time Document Retrieval (HSRDR); (2) passage retrieval, identifying optimal pairings of dense retrievers and rerankers; and (3) semantic representation, introducing Semantic Enhanced Overlap Segmentation (SEOS) for improved contextual understanding. On a custom-developed dataset tailored for cancer-related inquiries, our optimized RAG approach improved the answer accuracy of Claude-3-haiku by 5.24% over chain-of-thought prompting and about 3% over a naive RAG setup. This study highlights the importance of domain-specific query optimization in realizing the full potential of RAG and provides a robust framework for building more accurate and reliable CPQA systems, advancing the development of RAG-based biomedical systems.