Metraipolis › archive › dc_afef320c2f17

HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification — arXiv:2608.07204

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07204
License (as archived)
CC0-1.0
Archived
2026-10-19T09:46:57.298Z
SHA-256 of the archived text
7de73d0e19c5cdb0f38085c1a1ba3310d5250995ceff5b5d8d767c1aa3eedc59
Stable URL of this page
https://metraipolis.com/documento/dc_afef320c2f17

How to cite

HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification — arXiv:2608.07204 — arXiv (en), https://arxiv.org/abs/2608.07204 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_afef320c2f17 (Metraipolis archive dc_afef320c2f17, sha256 7de73d0e19c5cdb0f38085c1a1ba3310d5250995ceff5b5d8d767c1aa3eedc59)
BibTeX
@misc{dcafef320c2f17,
  title = {HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification — arXiv:2608.07204},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07204},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_afef320c2f17; sha256 7de73d0e19c5cdb0f38085c1a1ba3310d5250995ceff5b5d8d767c1aa3eedc59},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07204. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific claim verification over a cited paper requires predicting the claim--paper relation and identifying the paragraphs that justify that prediction. This setting poses two linked challenges: within-paper distractors often resemble genuine evidence, while a classifier trained on gold evidence must operate on retrieved evidence at inference. We present HNR-DAC, a two-stage framework that trains each stage on the cases it will actually encounter. Hard-Negative Reranking (HNR) quantifies evidence confusability using a base reranker's scores on non-gold paragraphs and contrasts gold evidence against the most confusable candidates. Distribution-Aligned Classification (DAC) trains on the Top-1 paragraph produced by the same frozen HNR used to construct inference inputs, while HNR's Top-3 paragraph identifiers provide the evidence output. On the NLPCC 2026 Task 10 Track 2, the final configuration obtains 97.21% Hit@3, 95.79% Macro-F1, 94.47% Joint@3, and an average score of 95.13%. The corresponding submission ranks third on the official Track 2 leaderboard while achieving the highest overall Macro-F1 of 93.05%, alongside 70.16% Joint@3 and an average score of 81.61%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.07204 — 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 2026-10-19T09:46:37.236Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).