@inproceedings{deutsch-etal-2025-wmt24,
title = "{WMT}24++: Expanding the Language Coverage of {WMT}24 to 55 Languages {\&} Dialects",
author = "Deutsch, Daniel and
Briakou, Eleftheria and
Caswell, Isaac Rayburn and
Finkelstein, Mara and
Galor, Rebecca and
Juraska, Juraj and
Kovacs, Geza and
Lui, Alison and
Rei, Ricardo and
Riesa, Jason and
Rijhwani, Shruti and
Riley, Parker and
Salesky, Elizabeth and
Trabelsi, Firas and
Winkler, Stephanie and
Zhang, Biao and
Freitag, Markus",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.634/",
doi = "10.18653/v1/2025.findings-acl.634",
pages = "12257--12284",
ISBN = "979-8-89176-256-5",
abstract = "As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages/dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. However, we caution against using our results to reach strong conclusions about MT quality without a human-based evaluation due to limitations of automatic evaluation metrics, which we leave for future work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deutsch-etal-2025-wmt24">
<titleInfo>
<title>WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Deutsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleftheria</namePart>
<namePart type="family">Briakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="given">Rayburn</namePart>
<namePart type="family">Caswell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Finkelstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Galor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juraj</namePart>
<namePart type="family">Juraska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geza</namePart>
<namePart type="family">Kovacs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alison</namePart>
<namePart type="family">Lui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Riesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parker</namePart>
<namePart type="family">Riley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firas</namePart>
<namePart type="family">Trabelsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Winkler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages/dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. However, we caution against using our results to reach strong conclusions about MT quality without a human-based evaluation due to limitations of automatic evaluation metrics, which we leave for future work.</abstract>
<identifier type="citekey">deutsch-etal-2025-wmt24</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.634</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.634/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>12257</start>
<end>12284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects
%A Deutsch, Daniel
%A Briakou, Eleftheria
%A Caswell, Isaac Rayburn
%A Finkelstein, Mara
%A Galor, Rebecca
%A Juraska, Juraj
%A Kovacs, Geza
%A Lui, Alison
%A Rei, Ricardo
%A Riesa, Jason
%A Rijhwani, Shruti
%A Riley, Parker
%A Salesky, Elizabeth
%A Trabelsi, Firas
%A Winkler, Stephanie
%A Zhang, Biao
%A Freitag, Markus
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F deutsch-etal-2025-wmt24
%X As large language models (LLM) become more and more capable in languages other than English, it is important to collect benchmark datasets in order to evaluate their multilingual performance, including on tasks like machine translation (MT). In this work, we extend the WMT24 dataset to cover 55 languages by collecting new human-written references and post-edits for 46 new languages/dialects in addition to post-edits of the references in 8 out of 9 languages in the original WMT24 dataset. We benchmark a variety of MT providers and LLMs on the collected dataset using automatic metrics and find that LLMs are the best-performing MT systems in all 55 languages. However, we caution against using our results to reach strong conclusions about MT quality without a human-based evaluation due to limitations of automatic evaluation metrics, which we leave for future work.
%R 10.18653/v1/2025.findings-acl.634
%U https://aclanthology.org/2025.findings-acl.634/
%U https://doi.org/10.18653/v1/2025.findings-acl.634
%P 12257-12284
Markdown (Informal)
[WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://aclanthology.org/2025.findings-acl.634/) (Deutsch et al., Findings 2025)
ACL
- Daniel Deutsch, Eleftheria Briakou, Isaac Rayburn Caswell, Mara Finkelstein, Rebecca Galor, Juraj Juraska, Geza Kovacs, Alison Lui, Ricardo Rei, Jason Riesa, Shruti Rijhwani, Parker Riley, Elizabeth Salesky, Firas Trabelsi, Stephanie Winkler, Biao Zhang, and Markus Freitag. 2025. WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects. In Findings of the Association for Computational Linguistics: ACL 2025, pages 12257–12284, Vienna, Austria. Association for Computational Linguistics.