@inproceedings{abuin-etal-2026-false,
title = "False {F}riends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for {G}alician, {P}ortuguese and {S}panish",
author = "Abu{\'i}n, Marta V{\'a}zquez and
Camacho-Collados, Jose and
Garcia, Marcos",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1818/",
pages = "39199--39214",
ISBN = "979-8-89176-390-6",
abstract = "The linguistic proximity between Galician, Portuguese, and Spanish results in a lexical overlap that often conceals semantic interference. This is particularly evident in false friends, posing a challenge for NLP systems.In this work, we assess whether state-of-the-art language models can identify and process false friends among these languages. We introduce six cross-lingual datasets {--}created manually or using semi-automatic methods, with all instances being carefully verified{--} covering cognates and false friends. We evaluate a broad range of encoder and decoder models of varying sizes via zero-shot and few-shot settings. Our results highlight the challenging nature of the task, but also show the clear progress made by LLMs in recent years, particularly those of a larger size, with smaller language models struggling on the task. Notably, unlike other tasks where language distance poses additional challenges, we find that linguistic proximity itself introduces errors: closely related language pairs tend to perform worse, reflecting the challenge of semantic discrimination due to lexical overlap."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abuin-etal-2026-false">
<titleInfo>
<title>False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">Vázquez</namePart>
<namePart type="family">Abuín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>The linguistic proximity between Galician, Portuguese, and Spanish results in a lexical overlap that often conceals semantic interference. This is particularly evident in false friends, posing a challenge for NLP systems.In this work, we assess whether state-of-the-art language models can identify and process false friends among these languages. We introduce six cross-lingual datasets –created manually or using semi-automatic methods, with all instances being carefully verified– covering cognates and false friends. We evaluate a broad range of encoder and decoder models of varying sizes via zero-shot and few-shot settings. Our results highlight the challenging nature of the task, but also show the clear progress made by LLMs in recent years, particularly those of a larger size, with smaller language models struggling on the task. Notably, unlike other tasks where language distance poses additional challenges, we find that linguistic proximity itself introduces errors: closely related language pairs tend to perform worse, reflecting the challenge of semantic discrimination due to lexical overlap.</abstract>
<identifier type="citekey">abuin-etal-2026-false</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1818/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>39199</start>
<end>39214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish
%A Abuín, Marta Vázquez
%A Camacho-Collados, Jose
%A Garcia, Marcos
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F abuin-etal-2026-false
%X The linguistic proximity between Galician, Portuguese, and Spanish results in a lexical overlap that often conceals semantic interference. This is particularly evident in false friends, posing a challenge for NLP systems.In this work, we assess whether state-of-the-art language models can identify and process false friends among these languages. We introduce six cross-lingual datasets –created manually or using semi-automatic methods, with all instances being carefully verified– covering cognates and false friends. We evaluate a broad range of encoder and decoder models of varying sizes via zero-shot and few-shot settings. Our results highlight the challenging nature of the task, but also show the clear progress made by LLMs in recent years, particularly those of a larger size, with smaller language models struggling on the task. Notably, unlike other tasks where language distance poses additional challenges, we find that linguistic proximity itself introduces errors: closely related language pairs tend to perform worse, reflecting the challenge of semantic discrimination due to lexical overlap.
%U https://aclanthology.org/2026.acl-long.1818/
%P 39199-39214
Markdown (Informal)
[False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish](https://aclanthology.org/2026.acl-long.1818/) (Abuín et al., ACL 2026)
ACL