@inproceedings{beauchemin-etal-2026-idiom,
title = "Idiom Understanding as a Tool to Measure the Dialect Gap",
author = "Beauchemin, David and
Tremblay, Yan and
Youssef, Mohamed Amine and
Khoury, Richard",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.24/",
pages = "505--522",
ISBN = "979-8-89176-395-1",
abstract = "The tasks of idiom understanding and dialect understanding are both well-established benchmarks in natural language processing. In this paper, we propose combining them, and using regional idioms as a test of dialect understanding. Towards this end, we propose three new benchmark datasets for the Quebec dialect of French: QFrCoRE, which contains 4,633 instances of idiomatic phrases, and QFrCoRT, which comprises 171 regional instances of idiomatic words, and a new benchmark for French Metropolitan expressions, MFrCoE, which comprises 4,938 phrases.We explain how to construct these corpora, so that our methodology can be replicated for other dialects. Our experiments with 111 LLMs reveal a critical disparity in dialectal competence: while models perform well on French Metropolitan, 65.77{\%} of them perform significantly worse on Quebec idioms, with only 9.0{\%} favoring the regional dialect. These results confirm that our benchmarks are a reliable tool for quantifying the dialect gap and that prestige-language proficiency does not guarantee regional dialect understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beauchemin-etal-2026-idiom">
<titleInfo>
<title>Idiom Understanding as a Tool to Measure the Dialect Gap</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Beauchemin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Tremblay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Amine</namePart>
<namePart type="family">Youssef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Khoury</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>The tasks of idiom understanding and dialect understanding are both well-established benchmarks in natural language processing. In this paper, we propose combining them, and using regional idioms as a test of dialect understanding. Towards this end, we propose three new benchmark datasets for the Quebec dialect of French: QFrCoRE, which contains 4,633 instances of idiomatic phrases, and QFrCoRT, which comprises 171 regional instances of idiomatic words, and a new benchmark for French Metropolitan expressions, MFrCoE, which comprises 4,938 phrases.We explain how to construct these corpora, so that our methodology can be replicated for other dialects. Our experiments with 111 LLMs reveal a critical disparity in dialectal competence: while models perform well on French Metropolitan, 65.77% of them perform significantly worse on Quebec idioms, with only 9.0% favoring the regional dialect. These results confirm that our benchmarks are a reliable tool for quantifying the dialect gap and that prestige-language proficiency does not guarantee regional dialect understanding.</abstract>
<identifier type="citekey">beauchemin-etal-2026-idiom</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.24/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>505</start>
<end>522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Idiom Understanding as a Tool to Measure the Dialect Gap
%A Beauchemin, David
%A Tremblay, Yan
%A Youssef, Mohamed Amine
%A Khoury, Richard
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F beauchemin-etal-2026-idiom
%X The tasks of idiom understanding and dialect understanding are both well-established benchmarks in natural language processing. In this paper, we propose combining them, and using regional idioms as a test of dialect understanding. Towards this end, we propose three new benchmark datasets for the Quebec dialect of French: QFrCoRE, which contains 4,633 instances of idiomatic phrases, and QFrCoRT, which comprises 171 regional instances of idiomatic words, and a new benchmark for French Metropolitan expressions, MFrCoE, which comprises 4,938 phrases.We explain how to construct these corpora, so that our methodology can be replicated for other dialects. Our experiments with 111 LLMs reveal a critical disparity in dialectal competence: while models perform well on French Metropolitan, 65.77% of them perform significantly worse on Quebec idioms, with only 9.0% favoring the regional dialect. These results confirm that our benchmarks are a reliable tool for quantifying the dialect gap and that prestige-language proficiency does not guarantee regional dialect understanding.
%U https://aclanthology.org/2026.findings-acl.24/
%P 505-522
Markdown (Informal)
[Idiom Understanding as a Tool to Measure the Dialect Gap](https://aclanthology.org/2026.findings-acl.24/) (Beauchemin et al., Findings 2026)
ACL
- David Beauchemin, Yan Tremblay, Mohamed Amine Youssef, and Richard Khoury. 2026. Idiom Understanding as a Tool to Measure the Dialect Gap. In Findings of the Association for Computational Linguistics: ACL 2026, pages 505–522, San Diego, California, United States. Association for Computational Linguistics.