Metraipolis › archive › dc_1ff02a0ba2e1

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval — arXiv:2609.07050

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07050
License (as archived)
CC0-1.0
Archived
2026-10-16T15:05:29.760Z
SHA-256 of the archived text
e0ebda329156b2eb010666a50810554beb57db9bd11c0900fab2713690049f95
Stable URL of this page
https://metraipolis.com/documento/dc_1ff02a0ba2e1

How to cite

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval — arXiv:2609.07050 — arXiv (en), https://arxiv.org/abs/2609.07050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1ff02a0ba2e1 (Metraipolis archive dc_1ff02a0ba2e1, sha256 e0ebda329156b2eb010666a50810554beb57db9bd11c0900fab2713690049f95)
BibTeX
@misc{dc1ff02a0ba2e1,
  title = {Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval — arXiv:2609.07050},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07050},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1ff02a0ba2e1; sha256 e0ebda329156b2eb010666a50810554beb57db9bd11c0900fab2713690049f95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularly challenging in multi-hop question answering (QA), where supporting passages are often linked through intermediate entities and relations that must be progressively uncovered. Existing retrieval approaches typically rely on a single retrieval intent or one-shot query expansion, limiting their ability to adapt to newly retrieved evidence and potentially introducing noisy or redundant retrieval signals. To address these limitations, we propose a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking. During offline indexing, the framework constructs passage-specific contrastive facets that characterize each passage relative to its semantically similar neighbors, providing fine-grained signals to distinguish closely related candidates. At inference time, the framework iteratively retrieves evidence, generates probes targeting unresolved information needs, refines candidate relevance using the contrastive facets, and selects a complementary set of passages that collectively cover diverse evidence-seeking intents. Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in retrieval quality and downstream QA performance over baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.IR).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.07050 — 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 2026-10-16T14:49:33.980Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).