KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR

TL;DR

This paper introduces a synthetic Kazakh OCR benchmark across three scripts and evaluates multimodal models, revealing their current limitations in recognizing low-resource Abjad-based scripts like Kazakh.

Contribution

It creates a novel synthetic dataset for Kazakh OCR in Arabic, Cyrillic, and Latin scripts and assesses multimodal models, highlighting their deficiencies in low-resource script recognition.

Findings

MLLMs fail to recognize Latin and Arabic Kazakh scripts.

Traditional OCR outperforms MLLMs in character error rates.

MLLMs misclassify Arabic script, showing gaps in low-resource language processing.

Abstract

Kazakh is a Turkic language using the Arabic, Cyrillic, and Latin scripts, making it unique in terms of optical character recognition (OCR). Work on OCR for low-resource Kazakh scripts is very scarce, and no OCR benchmarks or images exist for the Arabic and Latin scripts. We construct a synthetic OCR dataset of 7,219 images for all three scripts with font, color, and noise variations to imitate real OCR tasks. We evaluated three multimodal large language models (MLLMs) on a subset of the benchmark for OCR and language identification: Gemma-3-12B-it, Qwen2.5-VL-7B-Instruct, and Llama-3.2-11B-Vision-Instruct. All models are unsuccessful with Latin and Arabic script OCR, and fail to recognize the Arabic script as Kazakh text, misclassifying it as Arabic, Farsi, and Kurdish. We further compare MLLMs with a classical OCR baseline and find that while traditional OCR has lower character error rates, MLLMs fail to match this performance. These findings show significant gaps in current MLLM capabilities to process low-resource Abjad-based scripts and demonstrate the need for inclusive models and benchmarks supporting low-resource scripts and languages.