Metraipolis › archive › dc_d5411bca692f

EvLink: Source-Grounded Evidence Linking for Graph RAG — arXiv:2609.29695

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29695
License (as archived)
CC0-1.0
Archived
2026-10-08T06:43:58.903Z
SHA-256 of the archived text
972243ae2c6e35eb26bafdf1427d33457a4d92da12812487c78a370c1ea04e5d
Stable URL of this page
https://metraipolis.com/documento/dc_d5411bca692f

How to cite

EvLink: Source-Grounded Evidence Linking for Graph RAG — arXiv:2609.29695 — arXiv (en), https://arxiv.org/abs/2609.29695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5411bca692f (Metraipolis archive dc_d5411bca692f, sha256 972243ae2c6e35eb26bafdf1427d33457a4d92da12812487c78a370c1ea04e5d)
BibTeX
@misc{dcd5411bca692f,
  title = {EvLink: Source-Grounded Evidence Linking for Graph RAG — arXiv:2609.29695},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29695},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5411bca692f; sha256 972243ae2c6e35eb26bafdf1427d33457a4d92da12812487c78a370c1ea04e5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph-based Retrieval-Augmented Generation (GraphRAG) supports multi-hop reasoning by organizing corpora into structured graphs. However, graph reachability often captures semantic association rather than evidence support, so a reachable passage may still fail to justify a required cross-passage transition. We propose EvLink, an evidence-linking retriever that preserves passages as retrievable evidence units and builds evidence-supported transitions between them. EvLink constructs two types of reliable links: relation-grounded evidence links justified by explicit source relations, and endpoint-alignment links serving as sourcebounded fallbacks. For retrieval, we introduce a two-stage retrieval strategy. First, bounded breadth-first search over source-grounded evidence links recovers bridge passages missed by similarity-based methods. Then, evidenceneed mining with noisy-OR coverage refinement selects a compact, non-redundant evidence set satisfying distinct question facets. Experiments on three multi-hop and two simple QA benchmarks show EvLink consistently outperforms leading GraphRAG baselines with average gains of 2.4 R@5, 1.9 EM, and 2.4 F1

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.29695 — 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 2026-10-08T06:09:07.187Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).