<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2025-uva">
    <titleInfo>
        <title>UvA-MT’s Participation in the WMT25 General Translation Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yan</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maya</namePart>
        <namePart type="given">Konstantinovna</namePart>
        <namePart type="family">Nachesa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seth</namePart>
        <namePart type="family">Aycock</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth 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">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-341-8</identifier>
    </relatedItem>
    <abstract>This paper presents UvA-MT’s submission to the WMT 2025 shared task on general machine translation, competing in the unconstrained track across all 16 translation directions. Unusually, this year we use only WMT25’s blind test set (source sentences only) to generate synthetic data for LLM training, and translations are produced using pure beam search for submission. Overall, our approach can be seen as a special variant of data distillation, motivated by two key considerations: (1) perfect domain alignment, where the training and test domains are distributionally identical; and (2) the strong teacher model, GPT-4o-mini, offers high-quality outputs as both a reliable reference and a fallback in case of mere memorization.Interestingly, the outputs of the resulting model, trained on Gemma3-12B using Best-of-N (BoN) outputs from GPT-4o-mini, outperform both original BoN outputs from GPT-4o-mini and Gemma3-12B in some high-resource languages across various metrics. We attribute this to a successful model ensemble, where the student model (Gemma3-12B) retains the strengths of the teacher (GPT-4o-mini) while implicitly avoiding their flaws.</abstract>
    <identifier type="citekey">wu-etal-2025-uva</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.45/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>688</start>
            <end>694</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T UvA-MT’s Participation in the WMT25 General Translation Shared Task
%A Wu, Di
%A Meng, Yan
%A Nachesa, Maya Konstantinovna
%A Aycock, Seth
%A Monz, Christof
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F wu-etal-2025-uva
%X This paper presents UvA-MT’s submission to the WMT 2025 shared task on general machine translation, competing in the unconstrained track across all 16 translation directions. Unusually, this year we use only WMT25’s blind test set (source sentences only) to generate synthetic data for LLM training, and translations are produced using pure beam search for submission. Overall, our approach can be seen as a special variant of data distillation, motivated by two key considerations: (1) perfect domain alignment, where the training and test domains are distributionally identical; and (2) the strong teacher model, GPT-4o-mini, offers high-quality outputs as both a reliable reference and a fallback in case of mere memorization.Interestingly, the outputs of the resulting model, trained on Gemma3-12B using Best-of-N (BoN) outputs from GPT-4o-mini, outperform both original BoN outputs from GPT-4o-mini and Gemma3-12B in some high-resource languages across various metrics. We attribute this to a successful model ensemble, where the student model (Gemma3-12B) retains the strengths of the teacher (GPT-4o-mini) while implicitly avoiding their flaws.
%U https://aclanthology.org/2025.wmt-1.45/
%P 688-694

Markdown (Informal)

[UvA-MT’s Participation in the WMT25 General Translation Shared Task](https://aclanthology.org/2025.wmt-1.45/) (Wu et al., WMT 2025)

• UvA-MT’s Participation in the WMT25 General Translation Shared Task (Wu et al., WMT 2025)

ACL

• Di Wu, Yan Meng, Maya Konstantinovna Nachesa, Seth Aycock, and Christof Monz. 2025. UvA-MT’s Participation in the WMT25 General Translation Shared Task. In Proceedings of the Tenth Conference on Machine Translation, pages 688–694, Suzhou, China. Association for Computational Linguistics.