Metraipolis › archive › dc_53295b445a21

Online Evidence-Containment Prediction over Text Spans under Distinct Queries — arXiv:2610.41384

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41384
License (as archived): CC0-1.0
Archived: 2026-11-02T07:08:50.570Z
SHA-256 of the archived text: 2765d870e747efbbda3d2e807a21514ae3efe4a9c1f95905af775edb6dbaf8f2
Stable URL of this page: https://metraipolis.com/documento/dc_53295b445a21

How to cite

Online Evidence-Containment Prediction over Text Spans under Distinct Queries — arXiv:2610.41384 — arXiv (en), https://arxiv.org/abs/2610.41384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53295b445a21 (Metraipolis archive dc_53295b445a21, sha256 2765d870e747efbbda3d2e807a21514ae3efe4a9c1f95905af775edb6dbaf8f2)

BibTeX

@misc{dc53295b445a21,
  title = {Online Evidence-Containment Prediction over Text Spans under Distinct Queries — arXiv:2610.41384},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41384},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53295b445a21; sha256 2765d870e747efbbda3d2e807a21514ae3efe4a9c1f95905af775edb6dbaf8f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evidence-grounded NLP systems often verify nested text regions sequentially, so verifying one region constrains others. We formalize this as Online Evidence-Containment Prediction (OECP): each candidate is predicted before exact verification and queried at most once. Span containment is exactly a triangular 2D product order, making OECP distinct-query online isotonic regression. With multiple admissible targets, worst-case regret is near-linear, $\widetilde{\Theta}(m_{\mathrm{eff}})$, in the effective scale given by endpoint-rank compression; a single fixed target, as in standard QA, admits an explicit polynomial-time learner with optimal $\Theta(\log m_{\mathrm{eff}})$ regret, run on real NQ episodes. On Natural Questions, containment yields a large deductive gain plus a smaller learned gain on unresolved candidates, reproduced across two backbones and DPR hierarchies. Expected Search-space Reduction (ESR) turns these probabilities into decisions, localizing evidence in fewer verifier calls on SciFact, ERASER, and DPR hierarchies; on DPR hierarchies under call budgets it outperforms four recent external selectors and raises fixed-reader F1 over learned and generator-greedy scheduling.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41384 — 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 2026-11-02T07:06:59.336Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).