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

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 the insufficient utilization of multi-perspective views embedded within domain-specific corpora, 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, which leverages machine learning techniques for professional perspectives extraction and intention-aware query rewriting from multiple domain viewpoints to enhance retrieval precision, thereby improving the effectiveness of the final inference. Experiments conducted on both retrieval and generation tasks demonstrate substantial improvements in generation quality while maintaining retrieval performance in complex, knowledge-dense scenarios.