@inproceedings{alkhowaiter-etal-2025-mind,
title = "Mind the Gap: A Review of {A}rabic Post-Training Datasets and Their Limitations",
author = "Alkhowaiter, Mohammed and
Alshahrani, Saied and
Alshahrani, Norah F and
Masoud, Reem I. and
Alzahrani, Alaa and
Alnuhait, Deema and
Alghamdi, Emad A. and
Almubarak, Khalid",
editor = "Darwish, Kareem and
Ali, Ahmed and
Abu Farha, Ibrahim and
Touileb, Samia and
Zitouni, Imed and
Abdelali, Ahmed and
Al-Ghamdi, Sharefah and
Alkhereyf, Sakhar and
Zaghouani, Wajdi and
Khalifa, Salam and
AlKhamissi, Badr and
Almatham, Rawan and
Hamed, Injy and
Alyafeai, Zaid and
Alowisheq, Areeb and
Inoue, Go and
Mrini, Khalil and
Alshammari, Waad",
booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.arabicnlp-main.26/",
pages = "323--337",
ISBN = "979-8-89176-352-4",
abstract = "Post-training has emerged as a crucial technique for aligning pre-trained Large Language Models (LLMs) with human instructions, significantly enhancing their performance across a wide range of tasks. Central to this process is the quality and diversity of post-training datasets. This paper presents a review of publicly available Arabic post-training datasets on the Hugging Face Hub, organized along four key dimensions: (1) LLM Capabilities (e.g., Question Answering, Translation, Reasoning, Summarization, Dialogue, Code Generation, and Function Calling); (2) Steerability (e.g., Persona and System Prompts); (3) Alignment (e.g., Cultural, Safety, Ethics, and Fairness); and (4) Robustness. Each dataset is rigorously evaluated based on popularity, practical adoption, recency and maintenance, documentation and annotation quality, licensing transparency, and scientific contribution. Our review revealed critical gaps in the development of Arabic post-training datasets, including limited task diversity, inconsistent or missing documentation and annotation, and low adoption across the community. Finally, the paper discusses the implications of these gaps on the progress of Arabic-centric LLMs and applications while providing concrete recommendations for future efforts in Arabic post-training dataset development."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkhowaiter-etal-2025-mind">
<titleInfo>
<title>Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Alkhowaiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saied</namePart>
<namePart type="family">Alshahrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norah</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Alshahrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Masoud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alaa</namePart>
<namePart type="family">Alzahrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deema</namePart>
<namePart type="family">Alnuhait</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emad</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Alghamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Almubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Third Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharefah</namePart>
<namePart type="family">Al-Ghamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Areeb</namePart>
<namePart type="family">Alowisheq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Waad</namePart>
<namePart type="family">Alshammari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-352-4</identifier>
</relatedItem>
<abstract>Post-training has emerged as a crucial technique for aligning pre-trained Large Language Models (LLMs) with human instructions, significantly enhancing their performance across a wide range of tasks. Central to this process is the quality and diversity of post-training datasets. This paper presents a review of publicly available Arabic post-training datasets on the Hugging Face Hub, organized along four key dimensions: (1) LLM Capabilities (e.g., Question Answering, Translation, Reasoning, Summarization, Dialogue, Code Generation, and Function Calling); (2) Steerability (e.g., Persona and System Prompts); (3) Alignment (e.g., Cultural, Safety, Ethics, and Fairness); and (4) Robustness. Each dataset is rigorously evaluated based on popularity, practical adoption, recency and maintenance, documentation and annotation quality, licensing transparency, and scientific contribution. Our review revealed critical gaps in the development of Arabic post-training datasets, including limited task diversity, inconsistent or missing documentation and annotation, and low adoption across the community. Finally, the paper discusses the implications of these gaps on the progress of Arabic-centric LLMs and applications while providing concrete recommendations for future efforts in Arabic post-training dataset development.</abstract>
<identifier type="citekey">alkhowaiter-etal-2025-mind</identifier>
<location>
<url>https://aclanthology.org/2025.arabicnlp-main.26/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>323</start>
<end>337</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations
%A Alkhowaiter, Mohammed
%A Alshahrani, Saied
%A Alshahrani, Norah F.
%A Masoud, Reem I.
%A Alzahrani, Alaa
%A Alnuhait, Deema
%A Alghamdi, Emad A.
%A Almubarak, Khalid
%Y Darwish, Kareem
%Y Ali, Ahmed
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%Y Zitouni, Imed
%Y Abdelali, Ahmed
%Y Al-Ghamdi, Sharefah
%Y Alkhereyf, Sakhar
%Y Zaghouani, Wajdi
%Y Khalifa, Salam
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Hamed, Injy
%Y Alyafeai, Zaid
%Y Alowisheq, Areeb
%Y Inoue, Go
%Y Mrini, Khalil
%Y Alshammari, Waad
%S Proceedings of The Third Arabic Natural Language Processing Conference
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-352-4
%F alkhowaiter-etal-2025-mind
%X Post-training has emerged as a crucial technique for aligning pre-trained Large Language Models (LLMs) with human instructions, significantly enhancing their performance across a wide range of tasks. Central to this process is the quality and diversity of post-training datasets. This paper presents a review of publicly available Arabic post-training datasets on the Hugging Face Hub, organized along four key dimensions: (1) LLM Capabilities (e.g., Question Answering, Translation, Reasoning, Summarization, Dialogue, Code Generation, and Function Calling); (2) Steerability (e.g., Persona and System Prompts); (3) Alignment (e.g., Cultural, Safety, Ethics, and Fairness); and (4) Robustness. Each dataset is rigorously evaluated based on popularity, practical adoption, recency and maintenance, documentation and annotation quality, licensing transparency, and scientific contribution. Our review revealed critical gaps in the development of Arabic post-training datasets, including limited task diversity, inconsistent or missing documentation and annotation, and low adoption across the community. Finally, the paper discusses the implications of these gaps on the progress of Arabic-centric LLMs and applications while providing concrete recommendations for future efforts in Arabic post-training dataset development.
%U https://aclanthology.org/2025.arabicnlp-main.26/
%P 323-337
Markdown (Informal)
[Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations](https://aclanthology.org/2025.arabicnlp-main.26/) (Alkhowaiter et al., ArabicNLP 2025)
ACL
- Mohammed Alkhowaiter, Saied Alshahrani, Norah F Alshahrani, Reem I. Masoud, Alaa Alzahrani, Deema Alnuhait, Emad A. Alghamdi, and Khalid Almubarak. 2025. Mind the Gap: A Review of Arabic Post-Training Datasets and Their Limitations. In Proceedings of The Third Arabic Natural Language Processing Conference, pages 323–337, Suzhou, China. Association for Computational Linguistics.