@inproceedings{alwajih-etal-2025-palm,
title = "Palm: A Culturally Inclusive and Linguistically Diverse Dataset for {A}rabic {LLM}s",
author = "Alwajih, Fakhraddin and
El Mekki, Abdellah and
Magdy, Samar Mohamed and
Elmadany, AbdelRahim A. and
Nacar, Omer and
Nagoudi, El Moatez Billah and
Abdel-Salam, Reem and
Atwany, Hanin and
Nafea, Youssef and
Yahya, Abdulfattah Mohammed and
Alhamouri, Rahaf and
Alsayadi, Hamzah A. and
Zayed, Hiba and
Shatnawi, Sara and
Sibaee, Serry and
Ech-chammakhy, Yasir and
Al-Dhabyani, Walid and
Ali, Marwa Mohamed and
Jarraya, Imen and
El-Shangiti, Ahmed Oumar and
Alraeesi, Aisha and
AL-Ghrawi, Mohammed Anwar and
Al-Batati, Abdulrahman S. and
Mohamed, Elgizouli and
Elgindi, Noha Taha and
Saeed, Muhammed and
Atou, Houdaifa and
Yahia, Issam Ait and
Bouayad, Abdelhak and
Machrouh, Mohammed and
Makouar, Amal and
Alkawi, Dania and
Mohamed, Mukhtar and
Abdelfadil, Safaa Taher and
Ounnoughene, Amine Ziad and
Rouabhia, Anfel and
Assi, Rwaa and
Sorkatti, Ahmed and
Tourad, Mohamedou Cheikh and
Koubaa, Anis and
Berrada, Ismail and
Jarrar, Mustafa and
Shehata, Shady and
Abdul-Mageed, Muhammad",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1579/",
doi = "10.18653/v1/2025.acl-long.1579",
pages = "32871--32894",
ISBN = "979-8-89176-251-0",
abstract = "As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce PALM, a year-long community-driven project covering all 22 Arab countries. The dataset contains instruction{--}response pairs in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world{---}each an author of this paper{---}PALM offers a broad, inclusive perspective. We use PALM to evaluate the cultural and dialectal capabilities of several frontier LLMs, revealing notable limitations: while closed-source LLMs generally perform strongly, they still exhibit flaws, and smaller open-source models face greater challenges. Furthermore, certain countries (e.g., Egypt, the UAE) appear better represented than others (e.g., Iraq, Mauritania, Yemen). Our annotation guidelines, code, and data are publicly available for reproducibility. More information about PALM is available on our project page: https://github.com/UBC-NLP/palm."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alwajih-etal-2025-palm">
<titleInfo>
<title>Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fakhraddin</namePart>
<namePart type="family">Alwajih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">El</namePart>
<namePart type="given">Moatez</namePart>
<namePart type="given">Billah</namePart>
<namePart type="family">Nagoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Abdel-Salam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanin</namePart>
<namePart type="family">Atwany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Nafea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulfattah</namePart>
<namePart type="given">Mohammed</namePart>
<namePart type="family">Yahya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahaf</namePart>
<namePart type="family">Alhamouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Alsayadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiba</namePart>
<namePart type="family">Zayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Shatnawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serry</namePart>
<namePart type="family">Sibaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasir</namePart>
<namePart type="family">Ech-chammakhy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Al-Dhabyani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwa</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imen</namePart>
<namePart type="family">Jarraya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Oumar</namePart>
<namePart type="family">El-Shangiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aisha</namePart>
<namePart type="family">Alraeesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Anwar</namePart>
<namePart type="family">AL-Ghrawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Al-Batati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elgizouli</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noha</namePart>
<namePart type="given">Taha</namePart>
<namePart type="family">Elgindi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammed</namePart>
<namePart type="family">Saeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houdaifa</namePart>
<namePart type="family">Atou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Issam</namePart>
<namePart type="given">Ait</namePart>
<namePart type="family">Yahia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelhak</namePart>
<namePart type="family">Bouayad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Machrouh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Makouar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dania</namePart>
<namePart type="family">Alkawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mukhtar</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Safaa</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Abdelfadil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amine</namePart>
<namePart type="given">Ziad</namePart>
<namePart type="family">Ounnoughene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anfel</namePart>
<namePart type="family">Rouabhia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rwaa</namePart>
<namePart type="family">Assi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Sorkatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamedou</namePart>
<namePart type="given">Cheikh</namePart>
<namePart type="family">Tourad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anis</namePart>
<namePart type="family">Koubaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Berrada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shady</namePart>
<namePart type="family">Shehata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</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>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce PALM, a year-long community-driven project covering all 22 Arab countries. The dataset contains instruction–response pairs in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world—each an author of this paper—PALM offers a broad, inclusive perspective. We use PALM to evaluate the cultural and dialectal capabilities of several frontier LLMs, revealing notable limitations: while closed-source LLMs generally perform strongly, they still exhibit flaws, and smaller open-source models face greater challenges. Furthermore, certain countries (e.g., Egypt, the UAE) appear better represented than others (e.g., Iraq, Mauritania, Yemen). Our annotation guidelines, code, and data are publicly available for reproducibility. More information about PALM is available on our project page: https://github.com/UBC-NLP/palm.</abstract>
<identifier type="citekey">alwajih-etal-2025-palm</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1579</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1579/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>32871</start>
<end>32894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs
%A Alwajih, Fakhraddin
%A El Mekki, Abdellah
%A Magdy, Samar Mohamed
%A Elmadany, AbdelRahim A.
%A Nacar, Omer
%A Nagoudi, El Moatez Billah
%A Abdel-Salam, Reem
%A Atwany, Hanin
%A Nafea, Youssef
%A Yahya, Abdulfattah Mohammed
%A Alhamouri, Rahaf
%A Alsayadi, Hamzah A.
%A Zayed, Hiba
%A Shatnawi, Sara
%A Sibaee, Serry
%A Ech-chammakhy, Yasir
%A Al-Dhabyani, Walid
%A Ali, Marwa Mohamed
%A Jarraya, Imen
%A El-Shangiti, Ahmed Oumar
%A Alraeesi, Aisha
%A AL-Ghrawi, Mohammed Anwar
%A Al-Batati, Abdulrahman S.
%A Mohamed, Elgizouli
%A Elgindi, Noha Taha
%A Saeed, Muhammed
%A Atou, Houdaifa
%A Yahia, Issam Ait
%A Bouayad, Abdelhak
%A Machrouh, Mohammed
%A Makouar, Amal
%A Alkawi, Dania
%A Mohamed, Mukhtar
%A Abdelfadil, Safaa Taher
%A Ounnoughene, Amine Ziad
%A Rouabhia, Anfel
%A Assi, Rwaa
%A Sorkatti, Ahmed
%A Tourad, Mohamedou Cheikh
%A Koubaa, Anis
%A Berrada, Ismail
%A Jarrar, Mustafa
%A Shehata, Shady
%A Abdul-Mageed, Muhammad
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F alwajih-etal-2025-palm
%X As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce PALM, a year-long community-driven project covering all 22 Arab countries. The dataset contains instruction–response pairs in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world—each an author of this paper—PALM offers a broad, inclusive perspective. We use PALM to evaluate the cultural and dialectal capabilities of several frontier LLMs, revealing notable limitations: while closed-source LLMs generally perform strongly, they still exhibit flaws, and smaller open-source models face greater challenges. Furthermore, certain countries (e.g., Egypt, the UAE) appear better represented than others (e.g., Iraq, Mauritania, Yemen). Our annotation guidelines, code, and data are publicly available for reproducibility. More information about PALM is available on our project page: https://github.com/UBC-NLP/palm.
%R 10.18653/v1/2025.acl-long.1579
%U https://aclanthology.org/2025.acl-long.1579/
%U https://doi.org/10.18653/v1/2025.acl-long.1579
%P 32871-32894
Markdown (Informal)
[Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs](https://aclanthology.org/2025.acl-long.1579/) (Alwajih et al., ACL 2025)
ACL
- Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy, AbdelRahim A. Elmadany, Omer Nacar, El Moatez Billah Nagoudi, Reem Abdel-Salam, Hanin Atwany, Youssef Nafea, Abdulfattah Mohammed Yahya, Rahaf Alhamouri, Hamzah A. Alsayadi, Hiba Zayed, Sara Shatnawi, Serry Sibaee, Yasir Ech-chammakhy, Walid Al-Dhabyani, Marwa Mohamed Ali, Imen Jarraya, Ahmed Oumar El-Shangiti, Aisha Alraeesi, Mohammed Anwar AL-Ghrawi, Abdulrahman S. Al-Batati, Elgizouli Mohamed, Noha Taha Elgindi, Muhammed Saeed, Houdaifa Atou, Issam Ait Yahia, Abdelhak Bouayad, Mohammed Machrouh, Amal Makouar, Dania Alkawi, Mukhtar Mohamed, Safaa Taher Abdelfadil, Amine Ziad Ounnoughene, Anfel Rouabhia, Rwaa Assi, Ahmed Sorkatti, Mohamedou Cheikh Tourad, Anis Koubaa, Ismail Berrada, Mustafa Jarrar, Shady Shehata, and Muhammad Abdul-Mageed. 2025. Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 32871–32894, Vienna, Austria. Association for Computational Linguistics.