@inproceedings{adjovi-etal-2026-multilingual,
title = "When Multilingual Embeddings Collapse: Representation Failure and Metric (Un)reliability for {H}ausa and Fongbe Machine Translation",
author = "Adjovi, Mahounan Pericles and
Eiselen, Roald and
Mitra, Prasenjit",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.30/",
pages = "377--385",
ISBN = "979-8-89176-469-9",
abstract = "Neural evaluation metrics for machine translation inherit their behaviour from the multilingual encoders beneath them, yet how those encoders represent low-resource African languages is rarely examined. We evaluate four large language models on English-to-Hausa and English-to-Fongbe translation across scales from 500 to 10,000 sentences, validate automatic metrics against native-speaker judgment, and then probe the multilingual representation space that neural metrics depend on. The central finding is a representation failure: XLM-R assigns near-identical vectors to semantically different texts in both languages (within-language cosine similarity above 0.99), so BERTScore cannot separate systems of visibly different quality, and COMET produces a ranking anomaly for Fongbe. This representation collapse, rather than any surface property of the languages, explains why embedding-based metrics are unreliable here. We further show that metric-human rank agreement is language-dependent, that stable system rankings require at least 2,500 sentences, and that inclusion of a language in an encoder{'}s pretraining set does not guarantee usable representations. We frame these results as evidence that multilingual evaluation must be validated at the representation level before it is trusted."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adjovi-etal-2026-multilingual">
<titleInfo>
<title>When Multilingual Embeddings Collapse: Representation Failure and Metric (Un)reliability for Hausa and Fongbe Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahounan</namePart>
<namePart type="given">Pericles</namePart>
<namePart type="family">Adjovi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roald</namePart>
<namePart type="family">Eiselen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasenjit</namePart>
<namePart type="family">Mitra</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>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Neural evaluation metrics for machine translation inherit their behaviour from the multilingual encoders beneath them, yet how those encoders represent low-resource African languages is rarely examined. We evaluate four large language models on English-to-Hausa and English-to-Fongbe translation across scales from 500 to 10,000 sentences, validate automatic metrics against native-speaker judgment, and then probe the multilingual representation space that neural metrics depend on. The central finding is a representation failure: XLM-R assigns near-identical vectors to semantically different texts in both languages (within-language cosine similarity above 0.99), so BERTScore cannot separate systems of visibly different quality, and COMET produces a ranking anomaly for Fongbe. This representation collapse, rather than any surface property of the languages, explains why embedding-based metrics are unreliable here. We further show that metric-human rank agreement is language-dependent, that stable system rankings require at least 2,500 sentences, and that inclusion of a language in an encoder’s pretraining set does not guarantee usable representations. We frame these results as evidence that multilingual evaluation must be validated at the representation level before it is trusted.</abstract>
<identifier type="citekey">adjovi-etal-2026-multilingual</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>377</start>
<end>385</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Multilingual Embeddings Collapse: Representation Failure and Metric (Un)reliability for Hausa and Fongbe Machine Translation
%A Adjovi, Mahounan Pericles
%A Eiselen, Roald
%A Mitra, Prasenjit
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F adjovi-etal-2026-multilingual
%X Neural evaluation metrics for machine translation inherit their behaviour from the multilingual encoders beneath them, yet how those encoders represent low-resource African languages is rarely examined. We evaluate four large language models on English-to-Hausa and English-to-Fongbe translation across scales from 500 to 10,000 sentences, validate automatic metrics against native-speaker judgment, and then probe the multilingual representation space that neural metrics depend on. The central finding is a representation failure: XLM-R assigns near-identical vectors to semantically different texts in both languages (within-language cosine similarity above 0.99), so BERTScore cannot separate systems of visibly different quality, and COMET produces a ranking anomaly for Fongbe. This representation collapse, rather than any surface property of the languages, explains why embedding-based metrics are unreliable here. We further show that metric-human rank agreement is language-dependent, that stable system rankings require at least 2,500 sentences, and that inclusion of a language in an encoder’s pretraining set does not guarantee usable representations. We frame these results as evidence that multilingual evaluation must be validated at the representation level before it is trusted.
%U https://aclanthology.org/2026.mrl-1.30/
%P 377-385
Markdown (Informal)
[When Multilingual Embeddings Collapse: Representation Failure and Metric (Un)reliability for Hausa and Fongbe Machine Translation](https://aclanthology.org/2026.mrl-1.30/) (Adjovi et al., MRL 2026)
ACL