<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zong-etal-2025-dlut">
    <titleInfo>
        <title>DLUT and GTCOM’s Large Language Model Based Translation System for WMT25</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Zong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Bei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wentao</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Conghu</namePart>
        <namePart type="family">Yuan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Degen</namePart>
        <namePart type="family">Huang</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 the submission from Dalian University of Technology (DLUT) and Global Tone Communication Technology Co., Ltd. (GTCOM) to the WMT25 General Machine Translation Task. Amidst the paradigm shift from specialized encoder-decoder models to general-purpose Large Language Models (LLMs), this work conducts a systematic comparison of both approaches across five language pairs. For traditional Neural Machine Translation (NMT), we build strong baselines using deep Transformer architectures enhanced with data augmentation. For the LLM paradigm, we explore zero-shot performance and two distinct supervised fine-tuning (SFT) strategies: direct translation and translation refinement. Our key findings reveal a significant discrepancy between lexical and semantic evaluation metrics: while strong NMT systems remain competitive in BLEU scores, fine-tuned LLMs demonstrate marked superiority in semantic fidelity as measured by COMET. Furthermore, we find that fine-tuning LLMs for direct translation is more effective than for refinement, suggesting that teaching the core task directly is preferable to correcting baseline outputs.</abstract>
    <identifier type="citekey">zong-etal-2025-dlut</identifier>
    <identifier type="doi">10.18653/v1/2025.wmt-1.49</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.49/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>732</start>
            <end>739</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DLUT and GTCOM’s Large Language Model Based Translation System for WMT25
%A Zong, Hao
%A Bei, Chao
%A Chen, Wentao
%A Yuan, Conghu
%A Liu, Huan
%A Huang, Degen
%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 zong-etal-2025-dlut
%X This paper presents the submission from Dalian University of Technology (DLUT) and Global Tone Communication Technology Co., Ltd. (GTCOM) to the WMT25 General Machine Translation Task. Amidst the paradigm shift from specialized encoder-decoder models to general-purpose Large Language Models (LLMs), this work conducts a systematic comparison of both approaches across five language pairs. For traditional Neural Machine Translation (NMT), we build strong baselines using deep Transformer architectures enhanced with data augmentation. For the LLM paradigm, we explore zero-shot performance and two distinct supervised fine-tuning (SFT) strategies: direct translation and translation refinement. Our key findings reveal a significant discrepancy between lexical and semantic evaluation metrics: while strong NMT systems remain competitive in BLEU scores, fine-tuned LLMs demonstrate marked superiority in semantic fidelity as measured by COMET. Furthermore, we find that fine-tuning LLMs for direct translation is more effective than for refinement, suggesting that teaching the core task directly is preferable to correcting baseline outputs.
%R 10.18653/v1/2025.wmt-1.49
%U https://aclanthology.org/2025.wmt-1.49/
%U https://doi.org/10.18653/v1/2025.wmt-1.49
%P 732-739

Markdown (Informal)

[DLUT and GTCOM’s Large Language Model Based Translation System for WMT25](https://aclanthology.org/2025.wmt-1.49/) (Zong et al., WMT 2025)

• DLUT and GTCOM’s Large Language Model Based Translation System for WMT25 (Zong et al., WMT 2025)

ACL

• Hao Zong, Chao Bei, Wentao Chen, Conghu Yuan, Huan Liu, and Degen Huang. 2025. DLUT and GTCOM’s Large Language Model Based Translation System for WMT25. In Proceedings of the Tenth Conference on Machine Translation, pages 732–739, Suzhou, China. Association for Computational Linguistics.