@inproceedings{gagnier-2006-large,
    title = "Large Language Model-Based Post-{OCR} Correction for Low-Resource {K}azakh Scripts",
    author = "Gagnier, Henry",
    editor = "Gorman, Kyle",
    booktitle = "Proceedings of the Third Workshop on Computation and Written Language ({CAWL} 2026) @ {LREC} 2026",
    month = jun,
    year = "2006",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/test-year-match/2026.cawl-1.8/",
    doi = "10.63317/3po3x6arfznn",
    pages = "79--88",
    abstract = "Kazakh is written in the Arabic, Cyrillic, and Latin script which present unique challenges for OCR and post-OCR correction research. Despite this complexity, NLP research on Kazakh and its low-resource scripts remains extremely scarce. We analyze common OCR error patterns in all three Kazakh scripts using Tesseract and evaluate four large language models (LLMs) for post-OCR correction using minimal, confusion-aware, and few-shot prompting strategies. Our results reveal three systematic, writing-system-driven failure modes in LLM-based post-OCR correction: script switching, hallucination, and instruction-following breakdown. Arabic script post-OCR correction remains unsuccessful across all setups. In the Cyrillic script, post-OCR correction improvements are minimal due to the high baseline OCR performance on Cyrillic. For the Latin script, few-shot prompting with Gemini 2.5 Flash yields substantial improvements, reducing CER by 8.58 points and WER by 32.49 points to levels better than high-resource Kazakh Cyrillic script OCR. These findings demonstrate that LLM post-OCR correction failure modes are predictable from writing system properties such as script resource asymmetry and co-existing script dominance and demonstrate the need for typology-aware evaluation frameworks for multi-script and under-resourced languages."
}