@inproceedings{mcgiff-etal-2026-irish,
title = "{I}rish-{BL}i{MP}: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting",
author = "Mcgiff, Josh and
Tran, Tung Khanh and
Mulcahy, William and
{\'O} Luin{\'i}n, D{\'a}ibhidh and
Dalzell, Jake and
N{\'i} Bhroin, R{\'o}is{\'i}n and
Burke, Adam and
O{'}Sullivan, Barry and
Nguyen, Hoang D. and
Nikolov, Nikola S.",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.359/",
doi = "10.63317/4krpnjca34as",
pages = "4575--4586",
abstract = "We present Irish-BLiMP (Irish Benchmark of Linguistic Minimal Pairs), the first dataset and framework designed for fine-grained evaluation of linguistic competence in the Irish language, an endangered language. Drawing on a variety of linguistic literature and grammar reference works, a team of fluent Irish speakers manually constructed and reviewed 1020 minimal pairs across a taxonomy of 11 linguistic features. We evaluate both existing Large Language Models (LLMs) and fluent human participants on their syntactic knowledge of Irish. Our findings show that humans outperform all models across all linguistic features, achieving 16.6{\%} higher accuracy on average. Moreover, a substantial performance gap of 18.1{\%} persists between open- and closed-source LLMs, with even the strongest model (gpt-5) reaching only 73.5{\%} accuracy compared to 90.1{\%} by human. Interestingly, human participants and models struggle on different aspects of Irish grammar, thus highlighting a difference in representation learned by the models. Overall, Irish-BLiMP provides the first systematic framework for evaluating the grammatical competence of LLMs in Irish and offers a valuable benchmark for advancing research on linguistic understanding in low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcgiff-etal-2026-irish">
<titleInfo>
<title>Irish-BLiMP: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Mcgiff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tung</namePart>
<namePart type="given">Khanh</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Mulcahy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dáibhidh</namePart>
<namePart type="family">Ó Luinín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jake</namePart>
<namePart type="family">Dalzell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Róisín</namePart>
<namePart type="family">Ní Bhroin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Burke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">O’Sullivan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Nikolov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Irish-BLiMP (Irish Benchmark of Linguistic Minimal Pairs), the first dataset and framework designed for fine-grained evaluation of linguistic competence in the Irish language, an endangered language. Drawing on a variety of linguistic literature and grammar reference works, a team of fluent Irish speakers manually constructed and reviewed 1020 minimal pairs across a taxonomy of 11 linguistic features. We evaluate both existing Large Language Models (LLMs) and fluent human participants on their syntactic knowledge of Irish. Our findings show that humans outperform all models across all linguistic features, achieving 16.6% higher accuracy on average. Moreover, a substantial performance gap of 18.1% persists between open- and closed-source LLMs, with even the strongest model (gpt-5) reaching only 73.5% accuracy compared to 90.1% by human. Interestingly, human participants and models struggle on different aspects of Irish grammar, thus highlighting a difference in representation learned by the models. Overall, Irish-BLiMP provides the first systematic framework for evaluating the grammatical competence of LLMs in Irish and offers a valuable benchmark for advancing research on linguistic understanding in low-resource languages.</abstract>
<identifier type="citekey">mcgiff-etal-2026-irish</identifier>
<identifier type="doi">10.63317/4krpnjca34as</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.359/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4575</start>
<end>4586</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Irish-BLiMP: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting
%A Mcgiff, Josh
%A Tran, Tung Khanh
%A Mulcahy, William
%A Ó Luinín, Dáibhidh
%A Dalzell, Jake
%A Ní Bhroin, Róisín
%A Burke, Adam
%A O’Sullivan, Barry
%A Nguyen, Hoang D.
%A Nikolov, Nikola S.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F mcgiff-etal-2026-irish
%X We present Irish-BLiMP (Irish Benchmark of Linguistic Minimal Pairs), the first dataset and framework designed for fine-grained evaluation of linguistic competence in the Irish language, an endangered language. Drawing on a variety of linguistic literature and grammar reference works, a team of fluent Irish speakers manually constructed and reviewed 1020 minimal pairs across a taxonomy of 11 linguistic features. We evaluate both existing Large Language Models (LLMs) and fluent human participants on their syntactic knowledge of Irish. Our findings show that humans outperform all models across all linguistic features, achieving 16.6% higher accuracy on average. Moreover, a substantial performance gap of 18.1% persists between open- and closed-source LLMs, with even the strongest model (gpt-5) reaching only 73.5% accuracy compared to 90.1% by human. Interestingly, human participants and models struggle on different aspects of Irish grammar, thus highlighting a difference in representation learned by the models. Overall, Irish-BLiMP provides the first systematic framework for evaluating the grammatical competence of LLMs in Irish and offers a valuable benchmark for advancing research on linguistic understanding in low-resource languages.
%R 10.63317/4krpnjca34as
%U https://aclanthology.org/2026.lrec-1.359/
%U https://doi.org/10.63317/4krpnjca34as
%P 4575-4586
Markdown (Informal)
[Irish-BLiMP: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting](https://aclanthology.org/2026.lrec-1.359/) (Mcgiff et al., LREC 2026)
ACL
- Josh Mcgiff, Tung Khanh Tran, William Mulcahy, Dáibhidh Ó Luinín, Jake Dalzell, Róisín Ní Bhroin, Adam Burke, Barry O’Sullivan, Hoang D. Nguyen, and Nikola S. Nikolov. 2026. Irish-BLiMP: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4575–4586, Palma de Mallorca, Spain. ELRA Language Resource Association.