@inproceedings{adeeba-etal-2026-urblimp,
title = "{U}r{BL}i{MP}: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in {U}rdu",
author = "Adeeba, Farah and
Dillon, Brian and
Sajjad, Hassan and
Bhatt, Rajesh",
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.29/",
pages = "602--617",
ISBN = "979-8-89176-395-1",
abstract = "Evaluating how large language models (LLMs) capture the grammatical structure of low-resource languages remains underexplored. This paper presents the Urdu Benchmark of Linguistic Minimal Pairs (UrBLiMP){---}a diagnostic suite of 5,696 minimal pairs that contrast grammatical acceptability across ten core syntactic and morpho-syntactic phenomena in Urdu. The dataset is constructed from the Urdu Treebank and diverse text corpora, and human validation achieves a 96.1{\%} inter-annotator agreement, confirming its reliability. We evaluate twenty one multilingual LLMs, including LLaMA-3-70B and Gemma-3-27B-PT, and additionally assess the proprietary GPT-4o model using grammar-prompting techniques. GPT-4o (grammar-prompted) attains the highest average accuracy (97.4{\%}), reaching near-human performance on regular phenomena such as aspect agreement and ergativity. However, all models continue to struggle with flexible syntactic patterns like word-order variation and long-distance subject{--}verb agreement. UrBLiMP provides the first controlled evaluation framework for probing morpho-syntactic competence in Urdu and highlights both the progress and remaining challenges of multilingual and proprietary LLMs in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adeeba-etal-2026-urblimp">
<titleInfo>
<title>UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farah</namePart>
<namePart type="family">Adeeba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Dillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajesh</namePart>
<namePart type="family">Bhatt</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>Evaluating how large language models (LLMs) capture the grammatical structure of low-resource languages remains underexplored. This paper presents the Urdu Benchmark of Linguistic Minimal Pairs (UrBLiMP)—a diagnostic suite of 5,696 minimal pairs that contrast grammatical acceptability across ten core syntactic and morpho-syntactic phenomena in Urdu. The dataset is constructed from the Urdu Treebank and diverse text corpora, and human validation achieves a 96.1% inter-annotator agreement, confirming its reliability. We evaluate twenty one multilingual LLMs, including LLaMA-3-70B and Gemma-3-27B-PT, and additionally assess the proprietary GPT-4o model using grammar-prompting techniques. GPT-4o (grammar-prompted) attains the highest average accuracy (97.4%), reaching near-human performance on regular phenomena such as aspect agreement and ergativity. However, all models continue to struggle with flexible syntactic patterns like word-order variation and long-distance subject–verb agreement. UrBLiMP provides the first controlled evaluation framework for probing morpho-syntactic competence in Urdu and highlights both the progress and remaining challenges of multilingual and proprietary LLMs in low-resource settings.</abstract>
<identifier type="citekey">adeeba-etal-2026-urblimp</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.29/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>602</start>
<end>617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu
%A Adeeba, Farah
%A Dillon, Brian
%A Sajjad, Hassan
%A Bhatt, Rajesh
%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 adeeba-etal-2026-urblimp
%X Evaluating how large language models (LLMs) capture the grammatical structure of low-resource languages remains underexplored. This paper presents the Urdu Benchmark of Linguistic Minimal Pairs (UrBLiMP)—a diagnostic suite of 5,696 minimal pairs that contrast grammatical acceptability across ten core syntactic and morpho-syntactic phenomena in Urdu. The dataset is constructed from the Urdu Treebank and diverse text corpora, and human validation achieves a 96.1% inter-annotator agreement, confirming its reliability. We evaluate twenty one multilingual LLMs, including LLaMA-3-70B and Gemma-3-27B-PT, and additionally assess the proprietary GPT-4o model using grammar-prompting techniques. GPT-4o (grammar-prompted) attains the highest average accuracy (97.4%), reaching near-human performance on regular phenomena such as aspect agreement and ergativity. However, all models continue to struggle with flexible syntactic patterns like word-order variation and long-distance subject–verb agreement. UrBLiMP provides the first controlled evaluation framework for probing morpho-syntactic competence in Urdu and highlights both the progress and remaining challenges of multilingual and proprietary LLMs in low-resource settings.
%U https://aclanthology.org/2026.findings-acl.29/
%P 602-617
Markdown (Informal)
[UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu](https://aclanthology.org/2026.findings-acl.29/) (Adeeba et al., Findings 2026)
ACL