@inproceedings{moosavi-monazzah-etal-2025-percul,
title = "{P}er{C}ul: A Story-Driven Cultural Evaluation of {LLM}s in {P}ersian",
author = "Moosavi Monazzah, Erfan and
Rahimzadeh, Vahid and
Yaghoobzadeh, Yadollah and
Shakery, Azadeh and
Pilehvar, Mohammad Taher",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.631/",
doi = "10.18653/v1/2025.naacl-long.631",
pages = "12670--12687",
ISBN = "979-8-89176-189-6",
abstract = "Large language models predominantly reflect Western cultures, largely due to the dominance of English-centric training data. This imbalance presents a significant challenge, as LLMs are increasingly used across diverse contexts without adequate evaluation of their cultural competence in non-English languages, including Persian. To address this gap, we introduce PerCul, a carefully constructed dataset designed to assess the sensitivity of LLMs toward Persian culture. PerCul features story-based, multiple-choice questions that capture culturally nuanced scenarios.Unlike existing benchmarks, PerCul is curated with input from native Persian annotators to ensure authenticity and to prevent the use of translation as a shortcut. We evaluate several state-of-the-art multilingual and Persian-specific LLMs, establishing a foundation for future research in cross-cultural NLP evaluation. Our experiments demonstrate a 11.3{\%} gap between best closed source model and layperson baseline while the gap increases to 21.3{\%} by using the best open-weight model. You can access the dataset from here:https://huggingface.co/datasets/teias-ai/percul"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moosavi-monazzah-etal-2025-percul">
<titleInfo>
<title>PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erfan</namePart>
<namePart type="family">Moosavi Monazzah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vahid</namePart>
<namePart type="family">Rahimzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadollah</namePart>
<namePart type="family">Yaghoobzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azadeh</namePart>
<namePart type="family">Shakery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Large language models predominantly reflect Western cultures, largely due to the dominance of English-centric training data. This imbalance presents a significant challenge, as LLMs are increasingly used across diverse contexts without adequate evaluation of their cultural competence in non-English languages, including Persian. To address this gap, we introduce PerCul, a carefully constructed dataset designed to assess the sensitivity of LLMs toward Persian culture. PerCul features story-based, multiple-choice questions that capture culturally nuanced scenarios.Unlike existing benchmarks, PerCul is curated with input from native Persian annotators to ensure authenticity and to prevent the use of translation as a shortcut. We evaluate several state-of-the-art multilingual and Persian-specific LLMs, establishing a foundation for future research in cross-cultural NLP evaluation. Our experiments demonstrate a 11.3% gap between best closed source model and layperson baseline while the gap increases to 21.3% by using the best open-weight model. You can access the dataset from here:https://huggingface.co/datasets/teias-ai/percul</abstract>
<identifier type="citekey">moosavi-monazzah-etal-2025-percul</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.631</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.631/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>12670</start>
<end>12687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian
%A Moosavi Monazzah, Erfan
%A Rahimzadeh, Vahid
%A Yaghoobzadeh, Yadollah
%A Shakery, Azadeh
%A Pilehvar, Mohammad Taher
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F moosavi-monazzah-etal-2025-percul
%X Large language models predominantly reflect Western cultures, largely due to the dominance of English-centric training data. This imbalance presents a significant challenge, as LLMs are increasingly used across diverse contexts without adequate evaluation of their cultural competence in non-English languages, including Persian. To address this gap, we introduce PerCul, a carefully constructed dataset designed to assess the sensitivity of LLMs toward Persian culture. PerCul features story-based, multiple-choice questions that capture culturally nuanced scenarios.Unlike existing benchmarks, PerCul is curated with input from native Persian annotators to ensure authenticity and to prevent the use of translation as a shortcut. We evaluate several state-of-the-art multilingual and Persian-specific LLMs, establishing a foundation for future research in cross-cultural NLP evaluation. Our experiments demonstrate a 11.3% gap between best closed source model and layperson baseline while the gap increases to 21.3% by using the best open-weight model. You can access the dataset from here:https://huggingface.co/datasets/teias-ai/percul
%R 10.18653/v1/2025.naacl-long.631
%U https://aclanthology.org/2025.naacl-long.631/
%U https://doi.org/10.18653/v1/2025.naacl-long.631
%P 12670-12687
Markdown (Informal)
[PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian](https://aclanthology.org/2025.naacl-long.631/) (Moosavi Monazzah et al., NAACL 2025)
ACL
- Erfan Moosavi Monazzah, Vahid Rahimzadeh, Yadollah Yaghoobzadeh, Azadeh Shakery, and Mohammad Taher Pilehvar. 2025. PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 12670–12687, Albuquerque, New Mexico. Association for Computational Linguistics.