<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2025-shy">
    <titleInfo>
        <title>Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mao</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bingxin</namePart>
        <namePart type="family">Qu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingyang</namePart>
        <namePart type="family">Song</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>In this paper, we present our submission to the WMT25 shared task on machine translation, for which we propose Synergy-enhanced policy optimization framework, named Shy. This novel two-phase training framework synergistically combines knowledge distillation and fusion via reinforcement learning.In the first phase, we introduce a multi-stage training framework that harnesses the complementary strengths of multiple state-of-the-art large language models to generate diverse, high-quality translation candidates. These candidates serve as pseudo-references to guide the supervised fine-tuning of our model, Hunyuan-7B, effectively distilling the collective knowledge of multiple expert systems into a single efficient model.In the second phase, we further refine the distilled model through Group Relative Policy Optimization, a reinforcement learning technique that employs a composite reward function. By calculating reward from multiple perspectives, our model ensures better alignment with human preferences and evaluation metrics.Extensive experiments across multiple language pairs demonstrate that our model Shy-hunyuan-MT yields substantial improvements in translation quality compared to baseline approaches. Notably, our framework achieves competitive performance comparable to that of state-of-the-art systems while maintaining computational efficiency through knowledge distillation and strategic ensemble.</abstract>
    <identifier type="citekey">zheng-etal-2025-shy</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.36/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>607</start>
            <end>613</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task
%A Zheng, Mao
%A Li, Zheng
%A Du, Yang
%A Qu, Bingxin
%A Song, Mingyang
%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 zheng-etal-2025-shy
%X In this paper, we present our submission to the WMT25 shared task on machine translation, for which we propose Synergy-enhanced policy optimization framework, named Shy. This novel two-phase training framework synergistically combines knowledge distillation and fusion via reinforcement learning.In the first phase, we introduce a multi-stage training framework that harnesses the complementary strengths of multiple state-of-the-art large language models to generate diverse, high-quality translation candidates. These candidates serve as pseudo-references to guide the supervised fine-tuning of our model, Hunyuan-7B, effectively distilling the collective knowledge of multiple expert systems into a single efficient model.In the second phase, we further refine the distilled model through Group Relative Policy Optimization, a reinforcement learning technique that employs a composite reward function. By calculating reward from multiple perspectives, our model ensures better alignment with human preferences and evaluation metrics.Extensive experiments across multiple language pairs demonstrate that our model Shy-hunyuan-MT yields substantial improvements in translation quality compared to baseline approaches. Notably, our framework achieves competitive performance comparable to that of state-of-the-art systems while maintaining computational efficiency through knowledge distillation and strategic ensemble.
%U https://aclanthology.org/2025.wmt-1.36/
%P 607-613

Markdown (Informal)

[Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task](https://aclanthology.org/2025.wmt-1.36/) (Zheng et al., WMT 2025)

• Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task (Zheng et al., WMT 2025)

ACL

• Mao Zheng, Zheng Li, Yang Du, Bingxin Qu, and Mingyang Song. 2025. Shy-hunyuan-MT at WMT25 General Machine Translation Shared Task. In Proceedings of the Tenth Conference on Machine Translation, pages 607–613, Suzhou, China. Association for Computational Linguistics.