Metraipolis › archive › dc_310089e5d2ab

ConRAG: Lightweight inference of multi-hop relations — arXiv:2609.35193

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35193
License (as archived)
CC0-1.0
Archived
2026-10-07T22:38:55.526Z
SHA-256 of the archived text
f20d7f7cacf54dd8b7fea0ca1e23b9ea12d942cc5c6e0a6a2573ab63878bcbef
Stable URL of this page
https://metraipolis.com/documento/dc_310089e5d2ab

How to cite

ConRAG: Lightweight inference of multi-hop relations — arXiv:2609.35193 — arXiv (en), https://arxiv.org/abs/2609.35193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_310089e5d2ab (Metraipolis archive dc_310089e5d2ab, sha256 f20d7f7cacf54dd8b7fea0ca1e23b9ea12d942cc5c6e0a6a2573ab63878bcbef)
BibTeX
@misc{dc310089e5d2ab,
  title = {ConRAG: Lightweight inference of multi-hop relations — arXiv:2609.35193},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35193},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_310089e5d2ab; sha256 f20d7f7cacf54dd8b7fea0ca1e23b9ea12d942cc5c6e0a6a2573ab63878bcbef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supporting evidence that explain a connection. This is a task that appears frequently in scientific research and other knowledge-intensive analyses. We formalise this setting as multi-hop relation inference: given two known endpoint entities, we aim to recover the bridge entities and evidence-grounded reasoning chains that connect them across a document corpus, and to generate an explanation grounded in the retrieved evidence. Existing multi-hop RAG systems typically seek an unknown answer entity rather than explicitly recovering the connection between two known endpoints and graph-based approaches often rely on costly LLM-extracted knowledge graphs that limit scalability to large document collections. We introduce ConRAG, which builds a lightweight entity-document graph from entity co-occurrence and LLM-based entity filtering. Its connective retrieval infers and semantically ranks paths between two endpoints. On MuSiQue and 2WikiMultiHopQA, ConRAG consistently improves bridge entity and reasoning chain recovery over strong RAG baselines, while reducing graph-indexing token cost by up to roughly 1.5 orders of magnitude. Our results show that endpoint-constrained path retrieval provides an effective and index-efficient approach to evidence-grounded relation discovery.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35193 — 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 2026-10-07T22:14:28.380Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).