# QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation

arXiv: https://arxiv.org/abs/2506.02295 · HTML: https://mlsanity.com/paper/2506.02295/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 4 of 4)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks](https://mlsanity.com/paper/2403.01031/) (2024)
- [Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks](https://mlsanity.com/paper/1812.11894/) (2018)
- [Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition](https://mlsanity.com/paper/2407.13559/) (2024)

## Built on by (most cited first, 5 of 5)

- [Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR](https://mlsanity.com/paper/2509.18174/) (2025)
- [Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding](https://mlsanity.com/paper/2511.04699/) (2025)
- [Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study](https://mlsanity.com/paper/2607.14041/) (2026)
- [DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding](https://mlsanity.com/paper/2601.19898/) (2026)
- [When Do VLMs Help Arabic Manuscript OCR? A Cross-Dataset Study](https://mlsanity.com/paper/2608.22366/) (2026)

## Abstract (arXiv)

The inherent complexities of Arabic script; its cursive nature, diacritical marks (tashkeel), and varied typography, pose persistent challenges for Optical Character Recognition (OCR). We present Qari-OCR, a series of vision-language models derived from Qwen2-VL-2B-Instruct, progressively optimized for Arabic through iterative fine-tuning on specialized synthetic datasets. Our leading model, QARI v0.2, establishes a new open-source state-of-the-art with a Word Error Rate (WER) of 0.160, Character Error Rate (CER) of 0.061, and BLEU score of 0.737 on diacritically-rich texts. Qari-OCR demonstrates superior handling of tashkeel, diverse fonts, and document layouts, alongside impressive performance on low-resolution images. Further explorations (QARI v0.3) showcase strong potential for structural document understanding and handwritten text. This work delivers a marked improvement in Arabic OCR accuracy and efficiency, with all models and datasets released to foster further research.