Vision Language Models Are Not (Yet) Spelling Correctors
Spelling correction from visual input poses unique challenges for vision language models (VLMs), as it requires not only detecting but also correcting textual errors directly within images. We present ReViCo (Real Visual Correction), the first benchmark that systematically evaluates VLMs on real-world visual spelling correction across Chinese and English. ReViCo contains naturally occurring errors collected from real-world image data and supports fine-grained evaluation at both image and token levels. Through comprehensive experiments on representative cascaded (Qwen) and native (InternVL) open-source models, as well as closed-source systems (GPT-4o, Claude), we show that current VLMs fall significantly short of human performance, particularly in correction. To address these limitations, we explore two solution paradigms: a Joint OCR-Correction pipeline and a Background Information enhanced approach, both of which yield consistent performance gains. Our analysis highlights fundamental limitations of existing architectures and provides actionable insights for advancing multimodal spelling correction.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors
The lack of large-scale datasets has been a major hindrance to the development of NLP tasks such as spelling correction and grammatical error correction (GEC). As a complementary new resource for these tasks, we present …
Grammatical Error CorrectionSpelling CorrectionWNSpell: a WordNet-Based Spell Corrector
This paper presents a standalone spell corrector, WNSpell, based on and written for WordNet. It is aimed at generating the best possible suggestion for a mistyped query but can also serve as an all-purpose spell correcto…
Detecting Clitics Related Orthographic Errors in Turkish
For the spell correction task, vocabulary based methods have been replaced with methods that take morphological and grammar rules into account. However, such tools are fairly immature, and, worse, non-existent for many l…
Sampling Correctors
In many situations, sample data is obtained from a noisy or imperfect source. In order to address such corruptions, this paper introduces the concept of a sampling corrector. Such algorithms use structure that the distri…
High-dimensional separability for one- and few-shot learning
This work is driven by a practical question: corrections of Artificial Intelligence (AI) errors. These corrections should be quick and non-iterative. To solve this problem without modification of a legacy AI system, we p…
Domain AdaptationFew-Shot LearningOne-Shot LearningVocal Bursts Intensity Prediction