Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
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, a novel hypergraph-based RAG
method that represents n-ary relational facts via hyperedges, and consists of
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. Our
data and code are publicly available at
https://github.com/LHRLAB/HyperGraphRAG.
Authors (12)
Haoran Luo
Haihong E
Guanting Chen
Yandan Zheng
Xiaobao Wu
Yikai Guo
+6 more
NeurIPS 2025
Key Contributions
Introduces HyperGraphRAG, a novel RAG method using hypergraphs to represent n-ary relational facts, overcoming the limitations of binary relations in standard and graph-based RAG. Experiments show it outperforms existing methods in accuracy, retrieval efficiency, and generation quality across diverse domains.
Business Value
Enables more accurate and efficient information retrieval and generation for complex domains with intricate relationships, leading to better decision support and knowledge discovery tools.