<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gagnier-2026-large">
    <titleInfo>
        <title>Large Language Model-Based Post-OCR Correction for Low-Resource Kazakh Scripts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Henry</namePart>
        <namePart type="family">Gagnier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on Computation and Written Language (CAWL 2026) @ LREC 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kyle</namePart>
            <namePart type="family">Gorman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">gagnier-2026-large</identifier>
    <identifier type="doi">10.63317/3po3x6arfznn</identifier>
    <location>
        <url>https://aclanthology.org/2026.cawl-1.8/</url>
    </location>
    <part>
        <date>2026-06</date>
        <extent unit="page">
            <start>79</start>
            <end>88</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Large Language Model-Based Post-OCR Correction for Low-Resource Kazakh Scripts
%A Gagnier, Henry
%Y Gorman, Kyle
%S Proceedings of the Third Workshop on Computation and Written Language (CAWL 2026) @ LREC 2026
%D 2026
%8 June
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F gagnier-2026-large
%X 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.
%R 10.63317/3po3x6arfznn
%U https://aclanthology.org/2026.cawl-1.8/
%U https://doi.org/10.63317/3po3x6arfznn
%P 79-88

Markdown (Informal)

[Large Language Model-Based Post-OCR Correction for Low-Resource Kazakh Scripts](https://aclanthology.org/2026.cawl-1.8/) (Gagnier, CAWL 2026)

• Large Language Model-Based Post-OCR Correction for Low-Resource Kazakh Scripts (Gagnier, CAWL 2026)

ACL

• Henry Gagnier. 2026. Large Language Model-Based Post-OCR Correction for Low-Resource Kazakh Scripts. In Proceedings of the Third Workshop on Computation and Written Language (CAWL 2026) @ LREC 2026, pages 79–88, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).