# PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language

arXiv: https://arxiv.org/abs/2505.10055 · HTML: https://mlsanity.com/paper/2505.10055/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 69 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 32)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [TextCaps: a Dataset for Image Captioning with Reading Comprehension](https://mlsanity.com/paper/2003.12462/) (2020)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding](https://mlsanity.com/paper/2306.17107/) (2023)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text](https://mlsanity.com/paper/2105.05486/) (2021)
- [MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering](https://mlsanity.com/paper/2405.11985/) (2024)
- [CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy](https://mlsanity.com/paper/2412.02210/) (2024)
- [On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering](https://mlsanity.com/paper/2002.10215/) (2020)
- [Focus Anywhere for Fine-grained Multi-page Document Understanding](https://mlsanity.com/paper/2405.14295/) (2024)
- [Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text](https://mlsanity.com/paper/2003.13962/) (2020)
- [From Prompts to Templates: A Systematic Prompt Template Analysis for Real-world LLMapps](https://mlsanity.com/paper/2504.02052/) (2025)
- [CAMEL-Bench: A Comprehensive Arabic LMM Benchmark](https://mlsanity.com/paper/2410.18976/) (2024)
- [KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding](https://mlsanity.com/paper/2502.14949/) (2025)
- [Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA](https://mlsanity.com/paper/2401.15847/) (2024)
- [Advancing Post-OCR Correction: A Comparative Study of Synthetic Data](https://mlsanity.com/paper/2408.02253/) (2024)
- [MMR: Evaluating Reading Ability of Large Multimodal Models](https://mlsanity.com/paper/2408.14594/) (2024)
- [OCR Improves Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2202.13274/) (2022)
- [OCR Synthetic Benchmark Dataset for Indic Languages](https://mlsanity.com/paper/2205.02543/) (2022)

## Abstract (arXiv)

This paper evaluates the performance of Large Multimodal Models (LMMs) on Optical Character Recognition (OCR) in the low-resource Pashto language. Natural Language Processing (NLP) in Pashto faces several challenges due to the cursive nature of its script and a scarcity of structured datasets. To address this, we developed a synthetic Pashto OCR dataset, PsOCR, consisting of one million images annotated with bounding boxes at word, line, and document levels, suitable for training and evaluating models based on different architectures, including Convolutional Neural Networks (CNNs) and Transformers. PsOCR covers variations across 1,000 unique font families, colors, image sizes, and layouts. A benchmark subset of 10K images was selected to evaluate the performance of several LMMs, including seven open-source models: DeepSeek's Janus, InternVL, MiniCPM, Florence, and Qwen (3B and 7B), and four closed-source models: GPT-4o, Gemini, Claude, and Grok. Experimental results demonstrate that Gemini achieves the best performance among all models, whereas among open-source models, Qwen-7B stands out. This work provides an insightful assessment of the capabilities and limitations of current LMMs for OCR tasks in Pashto and establishes a foundation for further research not only in Pashto OCR but also for other similar scripts such as Arabic, Persian, and Urdu. PsOCR is available at https://github.com/zirak-ai/PashtoOCR.