While standard Retrieval-Augmented Generation (RAG) based on chunks, GraphRAG structures knowledge as graphs to leverage the relations among entities. However, previous GraphRAG methods are limited by binary relations: one edge in the graph only connects two entities, which cannot well model the n-ary relations among more than two entities that widely exist in reality. To address this limitation, we propose HyperGraphRAG, a novel hypergraph-based RAG method that represents n-ary relational facts via hyperedges, modeling the complicated n-ary relations in the real world. To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism. Experiments across medicine, agriculture, computer science, and law demonstrate that HyperGraphRAG outperforms standard RAG and GraphRAG in accuracy and generation quality.
View on arXiv@article{luo2025_2503.21322,
title={ HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation },
author={ Haoran Luo and Haihong E and Guanting Chen and Yandan Zheng and Xiaobao Wu and Yikai Guo and Qika Lin and Yu Feng and Zemin Kuang and Meina Song and Yifan Zhu and Luu Anh Tuan },
journal={arXiv preprint arXiv:2503.21322},
year={ 2025 }
}