Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation

TL;DR

This paper presents MVRAG, a multi-view retrieval framework for knowledge-dense domains that uses intention-aware query rewriting to improve retrieval accuracy and interpretability in legal and medical applications.

Contribution

Introduces a novel multi-view RAG framework that incorporates intention-aware query rewriting for enhanced retrieval in knowledge-dense fields.

Findings

Significant improvements in recall and precision in legal and medical retrieval tasks.

Multi-view retrieval enhances interpretability and reliability of RAG systems.

Framework accelerates application of LLMs in knowledge-intensive domains.

Abstract

While Retrieval-Augmented Generation (RAG) plays a crucial role in the application of Large Language Models (LLMs), existing retrieval methods in knowledge-dense domains like law and medicine still suffer from a lack of multi-perspective views, which are essential for improving interpretability and reliability. Previous research on multi-view retrieval often focused solely on different semantic forms of queries, neglecting the expression of specific domain knowledge perspectives. This paper introduces a novel multi-view RAG framework, MVRAG, tailored for knowledge-dense domains that utilizes intention-aware query rewriting from multiple domain viewpoints to enhance retrieval precision, thereby improving the effectiveness of the final inference. Experiments conducted on legal and medical case retrieval demonstrate significant improvements in recall and precision rates with our framework. Our multi-perspective retrieval approach unleashes the potential of multi-view information enhancing RAG tasks, accelerating the further application of LLMs in knowledge-intensive fields.