Retrieval-Augmented Generation with Hierarchical Knowledge
This addresses a problem for domain-specific tasks using RAG systems, but appears incremental as it builds on existing RAG methods.
The paper tackles the limitation of existing graph-based Retrieval-Augmented Generation (RAG) methods by not utilizing hierarchical knowledge, introducing HiRAG to enhance semantic understanding and structure capturing, and shows it achieves significant performance improvements over state-of-the-art baselines.
Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks. However, existing RAG methods do not adequately utilize the naturally inherent hierarchical knowledge in human cognition, which limits the capabilities of RAG systems. In this paper, we introduce a new RAG approach, called HiRAG, which utilizes hierarchical knowledge to enhance the semantic understanding and structure capturing capabilities of RAG systems in the indexing and retrieval processes. Our extensive experiments demonstrate that HiRAG achieves significant performance improvements over the state-of-the-art baseline methods.