HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
Nanyang Technological University · Beijing University of Post and Telecommunication · Beijing University of Posts and Telecommunications · Beijing Institute of Computer Technology and Application · National University of Singapore · China Mobile Research Institute · Capital Medical University · Nanyang Technological University, Singapore
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.