@inproceedings{zubiaga-etal-2026-towards,
title = "Towards Reliable Multilingual Judge Models: An Empirical Study",
author = "Zubiaga, Irune and
Soroa, Aitor and
Agerri, Rodrigo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.32/",
pages = "630--644",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) are increasingly used for automatic evaluation of generated text, but most work focuses on English. Extending LLM-based evaluation to multilingual settings is challenging, especially for low-resource languages or when in-domain data is scarce. This work explores how an English evaluation corpus can serve to evaluate other languages, both when in-domain data is available for fine-tuning and when it is not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and low-resource languages, considering instruction translation, monolingual versus multilingual supervision, and model size. Our results reveal key trade-offs: When in-domain data is available, fine-tuned smaller models can achieve performance comparable to proprietary models, whereas zero-shot evaluation with larger models proves more effective in out-of-domain settings. We also observe that fine-tuning on out-of-domain data can adversely affect model performance. These findings provide practical guidance for building efficient, reliable multilingual evaluation pipelines. The data and code are publicly available at hitz-zentroa/mJudge ."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zubiaga-etal-2026-towards">
<titleInfo>
<title>Towards Reliable Multilingual Judge Models: An Empirical Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irune</namePart>
<namePart type="family">Zubiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Agerri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used for automatic evaluation of generated text, but most work focuses on English. Extending LLM-based evaluation to multilingual settings is challenging, especially for low-resource languages or when in-domain data is scarce. This work explores how an English evaluation corpus can serve to evaluate other languages, both when in-domain data is available for fine-tuning and when it is not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and low-resource languages, considering instruction translation, monolingual versus multilingual supervision, and model size. Our results reveal key trade-offs: When in-domain data is available, fine-tuned smaller models can achieve performance comparable to proprietary models, whereas zero-shot evaluation with larger models proves more effective in out-of-domain settings. We also observe that fine-tuning on out-of-domain data can adversely affect model performance. These findings provide practical guidance for building efficient, reliable multilingual evaluation pipelines. The data and code are publicly available at hitz-zentroa/mJudge .</abstract>
<identifier type="citekey">zubiaga-etal-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.32/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>630</start>
<end>644</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Reliable Multilingual Judge Models: An Empirical Study
%A Zubiaga, Irune
%A Soroa, Aitor
%A Agerri, Rodrigo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zubiaga-etal-2026-towards
%X Large language models (LLMs) are increasingly used for automatic evaluation of generated text, but most work focuses on English. Extending LLM-based evaluation to multilingual settings is challenging, especially for low-resource languages or when in-domain data is scarce. This work explores how an English evaluation corpus can serve to evaluate other languages, both when in-domain data is available for fine-tuning and when it is not. We systematically analyze English, Spanish, and Basque, representing high-, mid-, and low-resource languages, considering instruction translation, monolingual versus multilingual supervision, and model size. Our results reveal key trade-offs: When in-domain data is available, fine-tuned smaller models can achieve performance comparable to proprietary models, whereas zero-shot evaluation with larger models proves more effective in out-of-domain settings. We also observe that fine-tuning on out-of-domain data can adversely affect model performance. These findings provide practical guidance for building efficient, reliable multilingual evaluation pipelines. The data and code are publicly available at hitz-zentroa/mJudge .
%U https://aclanthology.org/2026.findings-emnlp.32/
%P 630-644
Markdown (Informal)
[Towards Reliable Multilingual Judge Models: An Empirical Study](https://aclanthology.org/2026.findings-emnlp.32/) (Zubiaga et al., Findings 2026)
ACL