Metraipolis › archive › dc_ece2aada6fcb

SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection — arXiv:2610.06708

Source: arXiv
Original: https://arxiv.org/abs/2610.06708
License (as archived): CC0-1.0
Archived: 2026-10-06T05:28:39.750Z
SHA-256 of the archived text: 1c752a82c8a09b3df905052a108812b6e159b787be7e76fd11745ce4c06217f6
Stable URL of this page: https://metraipolis.com/documento/dc_ece2aada6fcb

How to cite

SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection — arXiv:2610.06708 — arXiv, https://arxiv.org/abs/2610.06708 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ece2aada6fcb (Metraipolis archive dc_ece2aada6fcb, sha256 1c752a82c8a09b3df905052a108812b6e159b787be7e76fd11745ce4c06217f6)

BibTeX

@misc{dcece2aada6fcb,
  title = {SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection — arXiv:2610.06708},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06708},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ece2aada6fcb; sha256 1c752a82c8a09b3df905052a108812b6e159b787be7e76fd11745ce4c06217f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06708. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal rumor detectors increasingly rely on retrieved evidence, yet relevant evidence is not necessarily sufficient for verification. Missing provenance, duplicated reports, and unresolved contradictions can produce confident predictions without adequate support. We introduce SAFE-MR, a framework that separates claim veracity from evidence sufficiency. The method decomposes image-text posts into verifiable claims, constructs a relation-aware claim-evidence graph, and aggregates evidence using provenance and contextual compatibility. Separate veracity and sufficiency heads support selective prediction, while evidence interventions encourage stability under irrelevant additions and sensitivity to evidence removal. On NewsCLIPpings, VERITE, and XFacta, SAFE-MR achieves macro-F1 scores of 91.2%, 75.8%, and 85.2%, respectively. Against the matched backbone with evidence, its macro-F1 gains are 2.2, 4.9, and 4.8 percentage points. On the diagnostic selection set, SAFE-MR reduces AURC from 0.105 for maximum-probability rejection to 0.075 and lowers error at 80% coverage from 13.8% to 8.5%. Evidence-perturbation and ablation results support the role of sufficiency learning and intervention training in improving selective verification.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.06708 — 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 2026-10-06T05:24:20.390Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).