Saved in:
Bibliographic Details
Main Authors: Huang, Haoyu, Huang, Yongfeng, Yang, Junjie, Pan, Zhenyu, Chen, Yongqiang, Ma, Kaili, Chen, Hongzhi, Cheng, James
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10150
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918148469424128
author Huang, Haoyu
Huang, Yongfeng
Yang, Junjie
Pan, Zhenyu
Chen, Yongqiang
Ma, Kaili
Chen, Hongzhi
Cheng, James
author_facet Huang, Haoyu
Huang, Yongfeng
Yang, Junjie
Pan, Zhenyu
Chen, Yongqiang
Ma, Kaili
Chen, Hongzhi
Cheng, James
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10150
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Retrieval-Augmented Generation with Hierarchical Knowledge
Huang, Haoyu
Huang, Yongfeng
Yang, Junjie
Pan, Zhenyu
Chen, Yongqiang
Ma, Kaili
Chen, Hongzhi
Cheng, James
Computation and Language
Artificial Intelligence
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.
title Retrieval-Augmented Generation with Hierarchical Knowledge
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.10150