@inproceedings{hassan-bhatti-alam-2026-beyond,
title = "Beyond {MCQ}: An Open-Ended {A}rabic Cultural {QA} Benchmark with Dialect Variants",
author = "Hassan Bhatti, Hunzalah and
Alam, Firoj",
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-1.408/",
doi = "10.63317/2smjp2wega4e",
pages = "5215--5231",
abstract = "Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains limited across languages and their varieties. We propose a comprehensive method that (i) translates Modern Standard Arabic (MSA) multiple-choice questions (MCQs) into English and several Arabic dialects, (ii) converts them into open-ended questions (OEQs), (iii) benchmarks a range of zero-shot and fine-tuned LLMs under both MCQ and OEQ settings, and (iv) generates chain-of-thought (CoT) rationales to fine-tune models for step-by-step reasoning. Using this method, we extend an existing dataset in which QAs are parallelly aligned across language varieties, making it, to our knowledge, the first of its kind. A large portion of the resulting test set is further validated through targeted human annotation and native-speaker post-editing. We conduct extensive experiments with both open and closed models. Our findings show that (i) models underperform on Arabic dialects, showing persistent gaps in culturally grounded and dialect-specific knowledge; (ii) Arabic-centric models perform well on MCQs but struggle with OEQs; and (iii) CoT improves judged correctness while yielding mixed n-gram-based metrics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hassan-bhatti-alam-2026-beyond">
<titleInfo>
<title>Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hunzalah</namePart>
<namePart type="family">Hassan Bhatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</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>Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains limited across languages and their varieties. We propose a comprehensive method that (i) translates Modern Standard Arabic (MSA) multiple-choice questions (MCQs) into English and several Arabic dialects, (ii) converts them into open-ended questions (OEQs), (iii) benchmarks a range of zero-shot and fine-tuned LLMs under both MCQ and OEQ settings, and (iv) generates chain-of-thought (CoT) rationales to fine-tune models for step-by-step reasoning. Using this method, we extend an existing dataset in which QAs are parallelly aligned across language varieties, making it, to our knowledge, the first of its kind. A large portion of the resulting test set is further validated through targeted human annotation and native-speaker post-editing. We conduct extensive experiments with both open and closed models. Our findings show that (i) models underperform on Arabic dialects, showing persistent gaps in culturally grounded and dialect-specific knowledge; (ii) Arabic-centric models perform well on MCQs but struggle with OEQs; and (iii) CoT improves judged correctness while yielding mixed n-gram-based metrics.</abstract>
<identifier type="citekey">hassan-bhatti-alam-2026-beyond</identifier>
<identifier type="doi">10.63317/2smjp2wega4e</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.408/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5215</start>
<end>5231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants
%A Hassan Bhatti, Hunzalah
%A Alam, Firoj
%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 hassan-bhatti-alam-2026-beyond
%X Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains limited across languages and their varieties. We propose a comprehensive method that (i) translates Modern Standard Arabic (MSA) multiple-choice questions (MCQs) into English and several Arabic dialects, (ii) converts them into open-ended questions (OEQs), (iii) benchmarks a range of zero-shot and fine-tuned LLMs under both MCQ and OEQ settings, and (iv) generates chain-of-thought (CoT) rationales to fine-tune models for step-by-step reasoning. Using this method, we extend an existing dataset in which QAs are parallelly aligned across language varieties, making it, to our knowledge, the first of its kind. A large portion of the resulting test set is further validated through targeted human annotation and native-speaker post-editing. We conduct extensive experiments with both open and closed models. Our findings show that (i) models underperform on Arabic dialects, showing persistent gaps in culturally grounded and dialect-specific knowledge; (ii) Arabic-centric models perform well on MCQs but struggle with OEQs; and (iii) CoT improves judged correctness while yielding mixed n-gram-based metrics.
%R 10.63317/2smjp2wega4e
%U https://aclanthology.org/2026.lrec-1.408/
%U https://doi.org/10.63317/2smjp2wega4e
%P 5215-5231
Markdown (Informal)
[Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants](https://aclanthology.org/2026.lrec-1.408/) (Hassan Bhatti & Alam, LREC 2026)
ACL