# CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition

arXiv: https://arxiv.org/abs/2509.19768 · HTML: https://mlsanity.com/paper/2509.19768/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 163 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition](https://mlsanity.com/paper/2309.15112/) (2023)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://mlsanity.com/paper/2406.18521/) (2024)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI](https://mlsanity.com/paper/2404.16006/) (2024)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy](https://mlsanity.com/paper/2412.02210/) (2024)
- [CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data](https://mlsanity.com/paper/2304.14953/) (2023)
- [R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning](https://mlsanity.com/paper/2508.21113/) (2025)
- [OCR4all -- An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings](https://mlsanity.com/paper/1909.04032/) (2019)
- [American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers](https://mlsanity.com/paper/2308.12477/) (2023)
- [ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family Records](https://mlsanity.com/paper/1903.03341/) (2019)
- [A Benchmark and Dataset for Post-OCR text correction in Sanskrit](https://mlsanity.com/paper/2211.07980/) (2022)
- [Optical Character Recognition of 19th Century Classical Commentaries: the Current State of Affairs](https://mlsanity.com/paper/2110.06817/) (2021)
- [WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data](https://mlsanity.com/paper/2312.10188/) (2023)
- [Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition](https://mlsanity.com/paper/2410.13305/) (2024)
- [On the Accuracy of CRNNs for Line-Based OCR: A Multi-Parameter Evaluation](https://mlsanity.com/paper/2008.02777/) (2020)
- [New Results for the Text Recognition of Arabic Maghrib=i Manuscripts -- Managing an Under-resourced Script](https://mlsanity.com/paper/2211.16147/) (2022)

## Built on by (most cited first, 9 of 9)

- [METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognition](https://mlsanity.com/paper/2605.26712/) (2026)
- [When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents](https://mlsanity.com/paper/2607.24077/) (2026)
- [The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions](https://mlsanity.com/paper/2603.09470/) (2026)
- [Quid est VERITAS? A Modular Framework for Archival Document Analysis](https://mlsanity.com/paper/2603.28108/) (2026)
- [Chronos: The AI Co-Historian](https://mlsanity.com/paper/2604.03553/) (2026)
- [Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press](https://mlsanity.com/paper/2608.05911/) (2026)
- [When Do VLMs Help Arabic Manuscript OCR? A Cross-Dataset Study](https://mlsanity.com/paper/2608.22366/) (2026)
- [ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts](https://mlsanity.com/paper/2609.12705/) (2026)
- [A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition](https://mlsanity.com/paper/2609.20064/) (2026)

## Abstract (arXiv)

Accurate text recognition for historical documents can greatly advance the study and preservation of cultural heritage. Existing vision-language models (VLMs), however, are designed for modern, standardized texts and are not equipped to read the diverse languages and scripts, irregular layouts, and frequent degradation found in historical materials. This paper presents CHURRO, a 3B-parameter open-weight VLM specialized for historical text recognition. The model is trained on CHURRO-DS, the largest historical text recognition dataset to date. CHURRO-DS unifies 155 historical corpora comprising 99,491 pages, spanning 22 centuries of textual heritage across 46 language clusters, including historical variants and dead languages. We evaluate several open-weight and closed VLMs and optical character recognition (OCR) systems on CHURRO-DS and find that CHURRO outperforms all other VLMs. On the CHURRO-DS test set, CHURRO achieves 82.3% (printed) and 70.1% (handwritten) normalized Levenshtein similarity, surpassing the second-best model, Gemini 2.5 Pro, by 1.4% and 6.5%, respectively, while being 15.5 times more cost-effective. By releasing the model and dataset, we aim to enable community-driven research to improve the readability of historical texts and accelerate scholarship.