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

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.

Authors

• Haoran Luo School of Computer Science, Beijing University of Posts and Telecommunications, China
• Haihong E School of Computer Science, Beijing University of Posts and Telecommunications
• Guanting Chen
• Yandan Zheng
• Xiaobao Wu Nanyang Technological University
• Yikai Guo Beijing Institute of Computer Technology and Application
• Qika Lin
• Yu Feng National University of Defense Technology
• Zemin Kuang
• Meina Song School of Computer Science, Beijing University of Posts and Telecommunications, China
• Yifan Zhu Beijing University of Posts and Telecommunications
• Anh Tuan Luu Nanyang Technological University

Keywords

No keywords are indexed for this paper.