Metraipolis › archive › dc_45988edde03e

Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning — arXiv:2609.00232

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00232
License (as archived): CC0-1.0
Archived: 2026-10-17T07:10:22.532Z
SHA-256 of the archived text: d3d8d11ed272bf1017be18faf82a330fda811dc2fa10767393465bfbb8e919da
Stable URL of this page: https://metraipolis.com/documento/dc_45988edde03e

How to cite

Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning — arXiv:2609.00232 — arXiv (en), https://arxiv.org/abs/2609.00232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45988edde03e (Metraipolis archive dc_45988edde03e, sha256 d3d8d11ed272bf1017be18faf82a330fda811dc2fa10767393465bfbb8e919da)

BibTeX

@misc{dc45988edde03e,
  title = {Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning — arXiv:2609.00232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45988edde03e; sha256 d3d8d11ed272bf1017be18faf82a330fda811dc2fa10767393465bfbb8e919da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmarks. Yet existing evaluations largely assume that every task is valid and answerable. In real-world OCR scenarios, this assumption often fails: questions may rely on illegible text, occluded evidence, nonexistent visual targets, contradictory premises, or missing variables. We study this reliability gap as OCR-grounded Task Verification: before answering, a model should determine whether the Image Premise (IP), Textual Premise (TP), and Question (Q) jointly define an executable task. We introduce VeriOCRBench, a 1,800-sample human-verified benchmark built from source images drawn from 8 OCR-related datasets and spanning 8 real-world image domains, with controlled, image-grounded diagnostic tasks. It contains 1,600 trap-injected invalid tasks across 8 trap types and four verification dimensions---Visual, Contextual, Factual, and Logical---plus 200 trap-free controls for measuring over-refusal. Built with a Visual Atomic Fact (VAF)-anchored pipeline and full human auditing, VeriOCRBench enables decoupled evaluation of task verification, root-cause diagnosis, and over-refusal. Evaluating 15 leading MLLMs reveals persistent blind compliance, diagnosis failures, and prompt-induced over-refusal, exposing a critical reliability gap in current OCR reasoning systems. The code is available at: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.00232 — 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 2026-10-17T07:00:58.894Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).