@inproceedings{gaido-etal-2025-findings,
title = "Findings of the {WMT} 2025 Shared Task on Model Compression: Early Insights on Compressing {LLM}s for Machine Translation",
author = "Gaido, Marco and
Grundkiewicz, Roman and
Gowda, Thamme and
Negri, Matteo",
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-1.25/",
pages = "484--494",
ISBN = "979-8-89176-341-8",
abstract = "We present the results of the first edition of the Model Compression shared task, organized as part of the 10th Conference on Machine Translation (WMT25). The task challenged participants to compress Large Language Models (LLMs) toward enabling practical deployment in resource-constrained scenarios, while minimizing loss in translation performance. In this edition, participants could choose to compete in either a constrained track, which required compressing a specific model (Aya Expanse 8B) evaluated on a limited set of language pairs (Czech{\textrightarrow}German, Japanese{\textrightarrow}Chinese, and English{\textrightarrow}Arabic), or an unconstrained track, which placed no restrictions on the model and allowed submissions for any of the 15 language directions covered by the General MT task (GenMT). We received 12 submissions from three teams, all in the constrained track. They proposed different compression solutions and covered various language combinations: all targeted Czech{\textrightarrow}German, while one covered all the language pairs. Evaluation was conducted separately for each language, measuring translation quality using COMET and MetricX, model size, and inference speed on an Nvidia A100 GPU."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaido-etal-2025-findings">
<titleInfo>
<title>Findings of the WMT 2025 Shared Task on Model Compression: Early Insights on Compressing LLMs for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Grundkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamme</namePart>
<namePart type="family">Gowda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</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>We present the results of the first edition of the Model Compression shared task, organized as part of the 10th Conference on Machine Translation (WMT25). The task challenged participants to compress Large Language Models (LLMs) toward enabling practical deployment in resource-constrained scenarios, while minimizing loss in translation performance. In this edition, participants could choose to compete in either a constrained track, which required compressing a specific model (Aya Expanse 8B) evaluated on a limited set of language pairs (Czech→German, Japanese→Chinese, and English→Arabic), or an unconstrained track, which placed no restrictions on the model and allowed submissions for any of the 15 language directions covered by the General MT task (GenMT). We received 12 submissions from three teams, all in the constrained track. They proposed different compression solutions and covered various language combinations: all targeted Czech→German, while one covered all the language pairs. Evaluation was conducted separately for each language, measuring translation quality using COMET and MetricX, model size, and inference speed on an Nvidia A100 GPU.</abstract>
<identifier type="citekey">gaido-etal-2025-findings</identifier>
<location>
<url>https://aclanthology.org/2025.wmt-1.25/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>484</start>
<end>494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the WMT 2025 Shared Task on Model Compression: Early Insights on Compressing LLMs for Machine Translation
%A Gaido, Marco
%A Grundkiewicz, Roman
%A Gowda, Thamme
%A Negri, Matteo
%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 gaido-etal-2025-findings
%X We present the results of the first edition of the Model Compression shared task, organized as part of the 10th Conference on Machine Translation (WMT25). The task challenged participants to compress Large Language Models (LLMs) toward enabling practical deployment in resource-constrained scenarios, while minimizing loss in translation performance. In this edition, participants could choose to compete in either a constrained track, which required compressing a specific model (Aya Expanse 8B) evaluated on a limited set of language pairs (Czech→German, Japanese→Chinese, and English→Arabic), or an unconstrained track, which placed no restrictions on the model and allowed submissions for any of the 15 language directions covered by the General MT task (GenMT). We received 12 submissions from three teams, all in the constrained track. They proposed different compression solutions and covered various language combinations: all targeted Czech→German, while one covered all the language pairs. Evaluation was conducted separately for each language, measuring translation quality using COMET and MetricX, model size, and inference speed on an Nvidia A100 GPU.
%U https://aclanthology.org/2025.wmt-1.25/
%P 484-494
Markdown (Informal)
[Findings of the WMT 2025 Shared Task on Model Compression: Early Insights on Compressing LLMs for Machine Translation](https://aclanthology.org/2025.wmt-1.25/) (Gaido et al., WMT 2025)
ACL