Metraipolis › archive › dc_ce64d58593df

Visual Sanad: Auditing Vision-Language Models for False Acceptance of Qur'anic Citations — arXiv:2610.22009

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22009
License (as archived)
CC0-1.0
Archived
2026-10-16T10:35:34.323Z
SHA-256 of the archived text
ccc3fcaff1af99e6b6faaa2c52e9c02089de114a21964c932772cff0ceef81fd
Stable URL of this page
https://metraipolis.com/documento/dc_ce64d58593df

How to cite

Visual Sanad: Auditing Vision-Language Models for False Acceptance of Qur'anic Citations — arXiv:2610.22009 — arXiv (en), https://arxiv.org/abs/2610.22009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce64d58593df (Metraipolis archive dc_ce64d58593df, sha256 ccc3fcaff1af99e6b6faaa2c52e9c02089de114a21964c932772cff0ceef81fd)
BibTeX
@misc{dcce64d58593df,
  title = {Visual Sanad: Auditing Vision-Language Models for False Acceptance of Qur'anic Citations — arXiv:2610.22009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce64d58593df; sha256 ccc3fcaff1af99e6b6faaa2c52e9c02089de114a21964c932772cff0ceef81fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) are increasingly used to interpret religious, educational, and culturally sensitive visual content, yet their reliability on citation verification remains underexplored. We introduce Visual Sanad, a controlled benchmark for testing whether VLMs falsely accept incorrect Qur'anic verse attributions when the same quote-reference pair is rendered under different visual framings. The benchmark contains 2,400 rendered images built from 100 English Qur'an verses, four factual states per verse, and six visual conditions ranging from plain text to decorative and authority-framed layouts. All quote-reference pairs were source-checked and human-audited before rendering. Across 24 full model-prompt runs, we observe a sharp capability split. Proprietary API-served VLMs range from near-perfect citation verification to moderate false acceptance, whereas recent open-weight VLMs often show weak discrimination and default to VALID on most images. De-biased prompting can reduce false acceptance, but often by shifting the decision threshold toward INVALID rather than by producing strong citation discrimination. Visual Sanad therefore exposes a culturally grounded multimodal factuality failure: fluent VLMs may treat displayed religious citations as self-authenticating unless they have strong citation-verification ability.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.22009 — 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 2026-10-16T08:52:02.712Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).