Retrieval-Augmented Generation with Hierarchical Knowledge

Haoyu Huang, Yongfeng Huang, Junjie Yang, Zhenyu Pan, Yongqiang Chen +3 more
3/13/2025
cs.CLcs.AI

No official code found. Best implementation: hhy-huang/HiRAG (551 stars, MIT, last commit 2025-11-19).

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.

View on arXivView PDF

Code Implementations(1)

hhy-huang/HiRAGCommunity100%
MIT

[EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.

55182PythonMar 14, 202511 months agoMIT
clusteringgraphraglarge-language-modelsnlprag+1 more

Similar Papers

A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models

89% match1 repo2.7k2025

A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions

88% match2024

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation

88% match2025

WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs

88% match2024

Retrieval-Augmented Generation for Natural Language Processing: A Survey

88% match2024

Knowledge Graph-Guided Retrieval Augmented Generation

88% match2 repos1362025

Cite this paper

@article{huang2025retrievalaugmented,
  title  = {Retrieval-Augmented Generation with Hierarchical Knowledge},
  author = {Haoyu Huang and Yongfeng Huang and Junjie Yang and Zhenyu Pan and Yongqiang Chen and Kaili Ma and Hongzhi Chen and James Cheng},
  year   = {2025},
  eprint = {2503.10150},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.10150v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.10150.svg)](https://codeofpaper.com/paper/2503.10150)

Discussion