# Vision Language Models Are Not (Yet) Spelling Correctors

arXiv: https://arxiv.org/abs/2509.17418 · HTML: https://mlsanity.com/paper/2509.17418/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs](https://mlsanity.com/paper/2502.17422/) (2025)
- [Spelling Error Correction with Soft-Masked BERT](https://mlsanity.com/paper/2005.07421/) (2020)
- [On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering](https://mlsanity.com/paper/2002.10215/) (2020)
- [SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check](https://mlsanity.com/paper/2004.14166/) (2020)
- [N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space](https://mlsanity.com/paper/2303.00456/) (2023)
- [Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture](https://mlsanity.com/paper/2509.02359/) (2025)
- [General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining](https://mlsanity.com/paper/2203.10929/) (2022)
- [Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters](https://mlsanity.com/paper/2311.11268/) (2023)
- [CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers](https://mlsanity.com/paper/2211.08788/) (2022)
- [A Benchmark and Dataset for Post-OCR text correction in Sanskrit](https://mlsanity.com/paper/2211.07980/) (2022)
- [Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments](https://mlsanity.com/paper/2502.06445/) (2025)
- [MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction](https://mlsanity.com/paper/2210.11720/) (2022)
- [Mixture of Small and Large Models for Chinese Spelling Check](https://mlsanity.com/paper/2506.06887/) (2025)
- [A Training-free LLM-based Approach to General Chinese Character Error Correction](https://mlsanity.com/paper/2502.15266/) (2025)
- [Chinese Spelling Correction: A Comprehensive Survey of Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2502.11508/) (2025)

## Built on by (most cited first, 1 of 1)

- [FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting](https://mlsanity.com/paper/2604.27974/) (2026)

## Abstract (arXiv)

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.