<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jon-etal-2026-cuni">
    <titleInfo>
        <title>CUNI-AR Team at WMT26 General Translation Task for Egyptian Arabic</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">Jon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rawan</namePart>
        <namePart type="family">Bondok</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Miroslav</namePart>
        <namePart type="family">Hrabal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Bojar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eleventh Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>We describe the Charles University CUNI-AR submission to the WMT26 General Translation shared task for English into Egyptian Arabic. Our pipeline is built around GEMBA (LLM-as-judge quality) estimator that scores translations independently for accuracy and dialect authenticity. We use it throughout our pipeline: to filter training data, to construct preference pairs for DPO, to select best checkpoints, and to pick the best hypothesis per segment at inference time. Our primary translation model is Gemma-4-12B-it finetuned via QLoRA, we also finetune Jais-2-8B-Chat and Aya-expanse-8B. Gemma-4-12B-it provides a high-quality Egyptian Arabic translation, so SFT yields only marginal quality gains in automatic metrics; DPO is able to improve the metrics it optimizes for, but the real gain in translation quality is to be assessed by human evaluation. The final submission selects the best-scoring translation per segment from 31 candidate checkpoints, with the unmodified base model contributing 31\textbackslash% of the output.</abstract>
    <identifier type="citekey">jon-etal-2026-cuni</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.68/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1271</start>
            <end>1283</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CUNI-AR Team at WMT26 General Translation Task for Egyptian Arabic
%A Jon, Josef
%A Bondok, Rawan
%A Hrabal, Miroslav
%A Bojar, Ondřej
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F jon-etal-2026-cuni
%X We describe the Charles University CUNI-AR submission to the WMT26 General Translation shared task for English into Egyptian Arabic. Our pipeline is built around GEMBA (LLM-as-judge quality) estimator that scores translations independently for accuracy and dialect authenticity. We use it throughout our pipeline: to filter training data, to construct preference pairs for DPO, to select best checkpoints, and to pick the best hypothesis per segment at inference time. Our primary translation model is Gemma-4-12B-it finetuned via QLoRA, we also finetune Jais-2-8B-Chat and Aya-expanse-8B. Gemma-4-12B-it provides a high-quality Egyptian Arabic translation, so SFT yields only marginal quality gains in automatic metrics; DPO is able to improve the metrics it optimizes for, but the real gain in translation quality is to be assessed by human evaluation. The final submission selects the best-scoring translation per segment from 31 candidate checkpoints, with the unmodified base model contributing 31\textbackslash% of the output.
%U https://aclanthology.org/2026.wmt-main.68/
%P 1271-1283

Markdown (Informal)

[CUNI-AR Team at WMT26 General Translation Task for Egyptian Arabic](https://aclanthology.org/2026.wmt-main.68/) (Jon et al., WMT 2026)

• CUNI-AR Team at WMT26 General Translation Task for Egyptian Arabic (Jon et al., WMT 2026)

ACL

• Josef Jon, Rawan Bondok, Miroslav Hrabal, and Ondřej Bojar. 2026. CUNI-AR Team at WMT26 General Translation Task for Egyptian Arabic. In Proceedings of the Eleventh Conference on Machine Translation, pages 1271–1283, Budapest, Hungary. Association for Computational Linguistics.