Metraipolis › archive › dc_a2fa4dd47422

HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning — arXiv:2609.32327

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.32327
License (as archived): CC0-1.0
Archived: 2026-10-07T20:55:19.467Z
SHA-256 of the archived text: 43a931a996cbc9b565c6024246c0d149d16db708774a145c4007e03db2fc71f2
Stable URL of this page: https://metraipolis.com/documento/dc_a2fa4dd47422

How to cite

HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning — arXiv:2609.32327 — arXiv (en), https://arxiv.org/abs/2609.32327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2fa4dd47422 (Metraipolis archive dc_a2fa4dd47422, sha256 43a931a996cbc9b565c6024246c0d149d16db708774a145c4007e03db2fc71f2)

BibTeX

@misc{dca2fa4dd47422,
  title = {HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning — arXiv:2609.32327},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32327},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2fa4dd47422; sha256 43a931a996cbc9b565c6024246c0d149d16db708774a145c4007e03db2fc71f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have shown strong capabilities, with retrieval-augmented generation (RAG) supporting complex multi-hop reasoning by retrieving evidence distributed across documents. Graph-based approaches exploit connections among evidence, and hypergraph-based retrieval further preserves higher-order entity associations within documents and connects documents through shared entities. However, existing hypergraph retrievers often rely on predefined structural expansion or diffusion, which may miss query-dependent interactions needed to identify relevant evidence. They also leave connections among retrieved evidence implicit, requiring LLMs to reconstruct these connections before reasoning. Therefore, we propose HyperReCo, a framework for retrieving and connecting evidence with a hypergraph neural network (HyperGNN). We represent each document as a hyperedge over its extracted entities, with shared entities connecting the hyperedges. Through hypergraph message passing with joint supervision over documents and entities, the HyperGNN learns query-dependent interactions to retrieve complementary evidence. We further introduce Gradient-Guided Hyper-Path Decoding (GGHD), which uses gradient attribution to interpret the learned interactions and translate them into explicit hyper-paths that help LLMs combine complementary facts for multi-hop reasoning. Experiments on six benchmarks show that HyperReCo achieves the best retrieval performance among the compared methods on all three multi-hop QA datasets, together with strong downstream QA performance. Case studies and further analyses demonstrate the utility of decoded hyper-paths for connecting retrieved evidence.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32327 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:00.757Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).