Salvato in:
Dettagli Bibliografici
Autori principali: Gong, Weile, Zuo, Yiping, Lu, Zijian, He, Xin, Fan, Weibei, Qi, Lianyong, Jin, Shi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.19790
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915937574191104
author Gong, Weile
Zuo, Yiping
Lu, Zijian
He, Xin
Fan, Weibei
Qi, Lianyong
Jin, Shi
author_facet Gong, Weile
Zuo, Yiping
Lu, Zijian
He, Xin
Fan, Weibei
Qi, Lianyong
Jin, Shi
contents Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-generation and unsupported substitutions, creating deployment risk even when benchmark accuracy remains high. We therefore formulate frozen VLM OCR as a selective accept/abstain problem and propose a model-agnostic Geometric Risk Controller. The controller probes multiple structured views of the same input, applies lightweight structural screening, and accepts a transcription only when cross-view consensus and stability satisfy predefined criteria, yielding a small family of operating points. Experiments on frozen VLM backbones and standard OCR benchmarks show consistent reductions in extreme-error risk and catastrophic over-generation at predictable coverage costs. Reliable deployment of generative OCR with frozen VLMs benefits from explicit system-level risk control rather than unconstrained generation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19790
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Plausibility to Verifiability: Risk-Controlled Generative OCR with Vision-Language Models
Gong, Weile
Zuo, Yiping
Lu, Zijian
He, Xin
Fan, Weibei
Qi, Lianyong
Jin, Shi
Computer Vision and Pattern Recognition
Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-generation and unsupported substitutions, creating deployment risk even when benchmark accuracy remains high. We therefore formulate frozen VLM OCR as a selective accept/abstain problem and propose a model-agnostic Geometric Risk Controller. The controller probes multiple structured views of the same input, applies lightweight structural screening, and accepts a transcription only when cross-view consensus and stability satisfy predefined criteria, yielding a small family of operating points. Experiments on frozen VLM backbones and standard OCR benchmarks show consistent reductions in extreme-error risk and catastrophic over-generation at predictable coverage costs. Reliable deployment of generative OCR with frozen VLMs benefits from explicit system-level risk control rather than unconstrained generation.
title From Plausibility to Verifiability: Risk-Controlled Generative OCR with Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.19790