Saved in:
Bibliographic Details
Main Authors: Lien, Wen-Sheng, Chan, Yu-Kai, Hsiao, Hao-Lung, Ruan, Bo-Kai, Chiang, Meng-Fen, Chen, Chien-An, Yeh, Yi-Ren, Shuai, Hong-Han
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.14470
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912906758586368
author Lien, Wen-Sheng
Chan, Yu-Kai
Hsiao, Hao-Lung
Ruan, Bo-Kai
Chiang, Meng-Fen
Chen, Chien-An
Yeh, Yi-Ren
Shuai, Hong-Han
author_facet Lien, Wen-Sheng
Chan, Yu-Kai
Hsiao, Hao-Lung
Ruan, Bo-Kai
Chiang, Meng-Fen
Chen, Chien-An
Yeh, Yi-Ren
Shuai, Hong-Han
contents Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. However, their rigid retrieval schemes and dense similarity search often introduce irrelevant context, increase computational overhead, and limit relational expressiveness. In contrast, n-ary hypergraphs encode higher-order relational facts that capture richer inter-entity dependencies and enable shallower, more efficient reasoning paths. To address this limitation, we propose HyperRAG, a RAG framework tailored for n-ary hypergraphs with two complementary retrieval variants: (i) HyperRetriever learns structural-semantic reasoning over n-ary facts to construct query-conditioned relational chains. It enables accurate factual tracking, adaptive high-order traversal, and interpretable multi-hop reasoning under context constraints. (ii) HyperMemory leverages the LLM's parametric memory to guide beam search, dynamically scoring n-ary facts and entities for query-aware path expansion. Extensive evaluations on WikiTopics (11 closed-domain datasets) and three open-domain QA benchmarks (HotpotQA, MuSiQue, and 2WikiMultiHopQA) validate HyperRAG's effectiveness. HyperRetriever achieves the highest answer accuracy overall, with average gains of 2.95% in MRR and 1.23% in Hits@10 over the strongest baseline. Qualitative analysis further shows that HyperRetriever bridges reasoning gaps through adaptive and interpretable n-ary chain construction, benefiting both open and closed-domain QA.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14470
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation
Lien, Wen-Sheng
Chan, Yu-Kai
Hsiao, Hao-Lung
Ruan, Bo-Kai
Chiang, Meng-Fen
Chen, Chien-An
Yeh, Yi-Ren
Shuai, Hong-Han
Computation and Language
Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. However, their rigid retrieval schemes and dense similarity search often introduce irrelevant context, increase computational overhead, and limit relational expressiveness. In contrast, n-ary hypergraphs encode higher-order relational facts that capture richer inter-entity dependencies and enable shallower, more efficient reasoning paths. To address this limitation, we propose HyperRAG, a RAG framework tailored for n-ary hypergraphs with two complementary retrieval variants: (i) HyperRetriever learns structural-semantic reasoning over n-ary facts to construct query-conditioned relational chains. It enables accurate factual tracking, adaptive high-order traversal, and interpretable multi-hop reasoning under context constraints. (ii) HyperMemory leverages the LLM's parametric memory to guide beam search, dynamically scoring n-ary facts and entities for query-aware path expansion. Extensive evaluations on WikiTopics (11 closed-domain datasets) and three open-domain QA benchmarks (HotpotQA, MuSiQue, and 2WikiMultiHopQA) validate HyperRAG's effectiveness. HyperRetriever achieves the highest answer accuracy overall, with average gains of 2.95% in MRR and 1.23% in Hits@10 over the strongest baseline. Qualitative analysis further shows that HyperRetriever bridges reasoning gaps through adaptive and interpretable n-ary chain construction, benefiting both open and closed-domain QA.
title HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2602.14470