@inproceedings{vahidi-pado-2026-cross,
title = "When Cross-Lingual Consistency Is Not Enough: Diagnostics for Low-Resource Political Actor Portrayal",
author = "Vahidi, Abdul Razaq and
Pad{\'o}, Sebastian",
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-1.25/",
pages = "310--319",
ISBN = "979-8-89176-469-9",
abstract = "The analysis of multilingual corpora with respect to political stance is of great interest to political science. However, it is a pri- ori unclear whether any differences found are genuinely cross-lingual in nature or artifacts of imperfect alignment, in particular for low- resource languages. In this study, we consider political actor portrayal in Dari and Pashto, the two main languages of Afghanistan. We work with a corpus of 200 quasi-parallel Dari{--}Pashto article pairs from a single outlet and evaluate the ability of three multilingual sentence-embedding models to make consistent cross-lingual predictions. We find that actor-level consistency differs substantially across models, and identical predicted labels can conceal differences in the underlying label-score profiles. We conclude that agreement alone is therefore insufficient for interpreting cross-lingual actor-portrayal predictions. This underlines the need for human validation before automatic cross-lingual predictions are used to support substantive conclusions about actor portrayal."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vahidi-pado-2026-cross">
<titleInfo>
<title>When Cross-Lingual Consistency Is Not Enough: Diagnostics for Low-Resource Political Actor Portrayal</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="given">Razaq</namePart>
<namePart type="family">Vahidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</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>The analysis of multilingual corpora with respect to political stance is of great interest to political science. However, it is a pri- ori unclear whether any differences found are genuinely cross-lingual in nature or artifacts of imperfect alignment, in particular for low- resource languages. In this study, we consider political actor portrayal in Dari and Pashto, the two main languages of Afghanistan. We work with a corpus of 200 quasi-parallel Dari–Pashto article pairs from a single outlet and evaluate the ability of three multilingual sentence-embedding models to make consistent cross-lingual predictions. We find that actor-level consistency differs substantially across models, and identical predicted labels can conceal differences in the underlying label-score profiles. We conclude that agreement alone is therefore insufficient for interpreting cross-lingual actor-portrayal predictions. This underlines the need for human validation before automatic cross-lingual predictions are used to support substantive conclusions about actor portrayal.</abstract>
<identifier type="citekey">vahidi-pado-2026-cross</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.25/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>310</start>
<end>319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Cross-Lingual Consistency Is Not Enough: Diagnostics for Low-Resource Political Actor Portrayal
%A Vahidi, Abdul Razaq
%A Padó, Sebastian
%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 vahidi-pado-2026-cross
%X The analysis of multilingual corpora with respect to political stance is of great interest to political science. However, it is a pri- ori unclear whether any differences found are genuinely cross-lingual in nature or artifacts of imperfect alignment, in particular for low- resource languages. In this study, we consider political actor portrayal in Dari and Pashto, the two main languages of Afghanistan. We work with a corpus of 200 quasi-parallel Dari–Pashto article pairs from a single outlet and evaluate the ability of three multilingual sentence-embedding models to make consistent cross-lingual predictions. We find that actor-level consistency differs substantially across models, and identical predicted labels can conceal differences in the underlying label-score profiles. We conclude that agreement alone is therefore insufficient for interpreting cross-lingual actor-portrayal predictions. This underlines the need for human validation before automatic cross-lingual predictions are used to support substantive conclusions about actor portrayal.
%U https://aclanthology.org/2026.mrl-1.25/
%P 310-319
Markdown (Informal)
[When Cross-Lingual Consistency Is Not Enough: Diagnostics for Low-Resource Political Actor Portrayal](https://aclanthology.org/2026.mrl-1.25/) (Vahidi & Padó, MRL 2026)
ACL