HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation

Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Zemin Kuang, Meina Song, Yifan Zhu, Anh Tuan Luu

Beijing University of Posts and Telecommunications· Nanyang Technological University· Beijing Institute of Computer Technology and Application· National University of Singapore· China Mobile Research Institute· Capital Medical University

Retrieval-Augumented Generation Hypergraph N-ary Relation Extraction Knowledge Representation

⋅ NeurIPS ⋅ Project Page ⋅Slides ⋅Poster ⋅OpenReview

Abstract

Standard Retrieval-Augmented Generation (RAG) relies on chunk-based retrieval, whereas GraphRAG advances this approach by graph-based knowledge representation. However, existing graph-based RAG approaches are constrained by binary relations, as each edge in an ordinary graph connects only two entities, limiting their ability to represent the n-ary relations (n >= 2) in real-world knowledge.

In this work, we propose HyperGraphRAG, the first hypergraph-based RAG method that represents n-ary relational facts via hyperedges. HyperGraphRAG consists of a comprehensive pipeline, including knowledge hypergraph construction, retrieval, and generation.

Experiments across medicine, agriculture, computer science, and law demonstrate that HyperGraphRAG outperforms both standard RAG and previous graph-based RAG methods in answer accuracy, retrieval efficiency, and generation quality.