Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Huang, Haoyu, Huang, Yongfeng, Yang, Junjie, Pan, Zhenyu, Chen, Yongqiang, Ma, Kaili, Chen, Hongzhi, Cheng, James
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979280843
Cites:
Cited by:
Related to: