@inproceedings{wang-etal-2025-marco,
title = "Marco Large Translation Model at {WMT}2025: Transforming Translation Capability in {LLM}s via Quality-Aware Training and Decoding",
author = "Wang, Hao and
Xu, Linlong and
Liu, Heng and
Liu, Yangyang and
Zhao, Xiaohu and
Zeng, Bo and
Wang, Longyue and
Luo, Weihua and
Zhang, Kaifu",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Tenth Conference on Machine Translation",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.wmt-1.33/",
pages = "587--593",
ISBN = "979-8-89176-341-8",
abstract = "This paper presents the Marco-MT-Algharb system, our submission to the WMT2025 General Machine Translation Shared Task from Alibaba International Digital Commerce (AIDC). Built on a large language model (LLM) foundation, the system{'}s strong performance stems from novel quality-aware training and decoding techniques: (1) a two-step supervised fine-tuning (SFT) process incorporating data distillation, (2) a two-step reinforcement learning (RL) framework for preference alignment, and (3) a hybrid decoding strategy that integrates word alignment with Minimum Bayes Risk (MBR) re-ranking to improve faithfulness. These approaches jointly ensure high accuracy and robustness across diverse languages and domains. In the official human evaluation, our system secured five first{-}place finishes, one second, and four third{-}place results in the constrained category across the 13 directions we participated in. Notably, for the English-Chinese, our results surpassed all open/closed{-}source systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-marco">
<titleInfo>
<title>Marco Large Translation Model at WMT2025: Transforming Translation Capability in LLMs via Quality-Aware Training and Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaifu</namePart>
<namePart type="family">Zhang</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 Marco-MT-Algharb system, our submission to the WMT2025 General Machine Translation Shared Task from Alibaba International Digital Commerce (AIDC). Built on a large language model (LLM) foundation, the system’s strong performance stems from novel quality-aware training and decoding techniques: (1) a two-step supervised fine-tuning (SFT) process incorporating data distillation, (2) a two-step reinforcement learning (RL) framework for preference alignment, and (3) a hybrid decoding strategy that integrates word alignment with Minimum Bayes Risk (MBR) re-ranking to improve faithfulness. These approaches jointly ensure high accuracy and robustness across diverse languages and domains. In the official human evaluation, our system secured five first-place finishes, one second, and four third-place results in the constrained category across the 13 directions we participated in. Notably, for the English-Chinese, our results surpassed all open/closed-source systems.</abstract>
<identifier type="citekey">wang-etal-2025-marco</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.33/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>587</start>
<end>593</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Marco Large Translation Model at WMT2025: Transforming Translation Capability in LLMs via Quality-Aware Training and Decoding
%A Wang, Hao
%A Xu, Linlong
%A Liu, Heng
%A Liu, Yangyang
%A Zhao, Xiaohu
%A Zeng, Bo
%A Wang, Longyue
%A Luo, Weihua
%A Zhang, Kaifu
%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 wang-etal-2025-marco
%X This paper presents the Marco-MT-Algharb system, our submission to the WMT2025 General Machine Translation Shared Task from Alibaba International Digital Commerce (AIDC). Built on a large language model (LLM) foundation, the system’s strong performance stems from novel quality-aware training and decoding techniques: (1) a two-step supervised fine-tuning (SFT) process incorporating data distillation, (2) a two-step reinforcement learning (RL) framework for preference alignment, and (3) a hybrid decoding strategy that integrates word alignment with Minimum Bayes Risk (MBR) re-ranking to improve faithfulness. These approaches jointly ensure high accuracy and robustness across diverse languages and domains. In the official human evaluation, our system secured five first-place finishes, one second, and four third-place results in the constrained category across the 13 directions we participated in. Notably, for the English-Chinese, our results surpassed all open/closed-source systems.
%U https://aclanthology.org/2025.wmt-1.33/
%P 587-593
Markdown (Informal)
[Marco Large Translation Model at WMT2025: Transforming Translation Capability in LLMs via Quality-Aware Training and Decoding](https://aclanthology.org/2025.wmt-1.33/) (Wang et al., WMT 2025)
ACL
- Hao Wang, Linlong Xu, Heng Liu, Yangyang Liu, Xiaohu Zhao, Bo Zeng, Longyue Wang, Weihua Luo, and Kaifu Zhang. 2025. Marco Large Translation Model at WMT2025: Transforming Translation Capability in LLMs via Quality-Aware Training and Decoding. In Proceedings of the Tenth Conference on Machine Translation, pages 587–593, Suzhou, China. Association for Computational Linguistics.