HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented Generation

RAIDS Lab Authors

Zhengyi Yang

(corresponding author)

Director

Details

Research Area

Tags

Resources

Abstract

Recent Hypergraph-based retrieval-augmented generation (HyperRAG) methods use hyperedges to connect multiple entities simultaneously, enabling more efficient multi-entity evidence organization than pairwise graph structures. However, existing HyperRAG methods often rely on LLM-generated summaries to construct hyperedges, which can introduce hallucinations while also incurring high indexing costs. In addition, during retrieval, existing methods typically rely on either one-hop neighbor expansion or PageRank diffusion. The former may miss useful multi-hop evidence, while the latter can suffer from uncontrolled propagation over excessive hub nodes, leading to semantic drift and noisy reasoning chains. To address these challenges, we propose HyperSU, a novel hypergraph-based RAG framework featuring semantic-unit hyperedges and clue-guided bidirectional retrieval. During construction, HyperSU formulates hyperedge construction as an entity-aware minimum-description-length (MDL) optimization problem, inducing source-grounded semantic-unit hyperedges that balance sentence-level semantic coherence and entity compactness. It then constructs a hypergraph by modeling each semantic unit as a hyperedge over its co-mentioned entities. During retrieval, HyperSU performs clue-guided bidirectional expansion over the semantic-unit hypergraph, enabling both multi-hop evidence discovery and evidence-anchored noise reduction. Experiments show that HyperSU consistently improves answer accuracy over standard, graph-based, and hypergraph-based RAG baselines, raising average accuracy on GraphRAG-Bench by 5.5 points over the strongest baseline (68.7 vs. 63.2), with larger gains on reasoning-intensive tasks, where the relative improvement reaches 14.1%. Our code is available at https://github.com/RAIDSLab/HyperSU.

Author Affiliations

@misc{liu2026hypersu,
  title = {HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented Generation},
  author = {Jiate Liu and Liuyi Chen and Zhengyi Yang and Chuan He and Mingchen Ju and Bocheng Han and Ruyi Liu and Xu Zhou},
  year = {2026},
  eprint = {2606.28351},
  archivePrefix = {arXiv},
  primaryClass = {cs.IR},
  url = {https://arxiv.org/abs/2606.28351}
}