@inproceedings{hasan-etal-2025-nativqa,
title = "{N}ativ{QA}: Multilingual Culturally-Aligned Natural Query for {LLM}s",
author = "Hasan, Md. Arid and
Hasanain, Maram and
Ahmad, Fatema and
Laskar, Sahinur Rahman and
Upadhyay, Sunaya and
Sukhadia, Vrunda N and
Kutlu, Mucahid and
Chowdhury, Shammur Absar and
Alam, Firoj",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.770/",
doi = "10.18653/v1/2025.findings-acl.770",
pages = "14886--14909",
ISBN = "979-8-89176-256-5",
abstract = "Natural Question Answering (QA) datasets play a crucial role in evaluating the capabilities of large language models (LLMs), ensuring their effectiveness in real-world applications. Despite the numerous QA datasets that have been developed and some work done in parallel, there is a notable lack of a framework and large-scale region-specific datasets queried by native users in their own languages. This gap hinders effective benchmarking and the development of fine-tuned models for regional and cultural specificities. In this study, we propose a scalable, language-independent framework, NativQA, to seamlessly construct culturally and regionally aligned QA datasets in native languages for LLM evaluation and tuning. We demonstrate the efficacy of the proposed framework by designing a multilingual natural QA dataset, MultiNativQA, consisting of approximately {\textasciitilde}64K manually annotated QA pairs in seven languages, ranging from high- to extremely low-resource, based on queries from native speakers from 9 regions covering 18 topics. We benchmark both open- and closed-source LLMs using the MultiNativQA dataset. The dataset and related experimental scripts are publicly available for the community at: https://huggingface.co/datasets/QCRI/MultiNativQAand https://gitlab.com/nativqa/multinativqa."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasan-etal-2025-nativqa">
<titleInfo>
<title>NativQA: Multilingual Culturally-Aligned Natural Query for LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Arid</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maram</namePart>
<namePart type="family">Hasanain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatema</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahinur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunaya</namePart>
<namePart type="family">Upadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vrunda</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Sukhadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mucahid</namePart>
<namePart type="family">Kutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</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>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Natural Question Answering (QA) datasets play a crucial role in evaluating the capabilities of large language models (LLMs), ensuring their effectiveness in real-world applications. Despite the numerous QA datasets that have been developed and some work done in parallel, there is a notable lack of a framework and large-scale region-specific datasets queried by native users in their own languages. This gap hinders effective benchmarking and the development of fine-tuned models for regional and cultural specificities. In this study, we propose a scalable, language-independent framework, NativQA, to seamlessly construct culturally and regionally aligned QA datasets in native languages for LLM evaluation and tuning. We demonstrate the efficacy of the proposed framework by designing a multilingual natural QA dataset, MultiNativQA, consisting of approximately ~64K manually annotated QA pairs in seven languages, ranging from high- to extremely low-resource, based on queries from native speakers from 9 regions covering 18 topics. We benchmark both open- and closed-source LLMs using the MultiNativQA dataset. The dataset and related experimental scripts are publicly available for the community at: https://huggingface.co/datasets/QCRI/MultiNativQAand https://gitlab.com/nativqa/multinativqa.</abstract>
<identifier type="citekey">hasan-etal-2025-nativqa</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.770</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.770/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>14886</start>
<end>14909</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NativQA: Multilingual Culturally-Aligned Natural Query for LLMs
%A Hasan, Md. Arid
%A Hasanain, Maram
%A Ahmad, Fatema
%A Laskar, Sahinur Rahman
%A Upadhyay, Sunaya
%A Sukhadia, Vrunda N.
%A Kutlu, Mucahid
%A Chowdhury, Shammur Absar
%A Alam, Firoj
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F hasan-etal-2025-nativqa
%X Natural Question Answering (QA) datasets play a crucial role in evaluating the capabilities of large language models (LLMs), ensuring their effectiveness in real-world applications. Despite the numerous QA datasets that have been developed and some work done in parallel, there is a notable lack of a framework and large-scale region-specific datasets queried by native users in their own languages. This gap hinders effective benchmarking and the development of fine-tuned models for regional and cultural specificities. In this study, we propose a scalable, language-independent framework, NativQA, to seamlessly construct culturally and regionally aligned QA datasets in native languages for LLM evaluation and tuning. We demonstrate the efficacy of the proposed framework by designing a multilingual natural QA dataset, MultiNativQA, consisting of approximately ~64K manually annotated QA pairs in seven languages, ranging from high- to extremely low-resource, based on queries from native speakers from 9 regions covering 18 topics. We benchmark both open- and closed-source LLMs using the MultiNativQA dataset. The dataset and related experimental scripts are publicly available for the community at: https://huggingface.co/datasets/QCRI/MultiNativQAand https://gitlab.com/nativqa/multinativqa.
%R 10.18653/v1/2025.findings-acl.770
%U https://aclanthology.org/2025.findings-acl.770/
%U https://doi.org/10.18653/v1/2025.findings-acl.770
%P 14886-14909
Markdown (Informal)
[NativQA: Multilingual Culturally-Aligned Natural Query for LLMs](https://aclanthology.org/2025.findings-acl.770/) (Hasan et al., Findings 2025)
ACL
- Md. Arid Hasan, Maram Hasanain, Fatema Ahmad, Sahinur Rahman Laskar, Sunaya Upadhyay, Vrunda N Sukhadia, Mucahid Kutlu, Shammur Absar Chowdhury, and Firoj Alam. 2025. NativQA: Multilingual Culturally-Aligned Natural Query for LLMs. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14886–14909, Vienna, Austria. Association for Computational Linguistics.