Palm：面向阿拉伯语言模型的文化包容性且语言多样性数据集
计算与语言
2025-07-28 v2 人工智能
摘要
随着大规模语言模型(LLM)日益融入日常生活，确保其文化敏感性和包容性至关重要。我们介绍自己的数据集，是一个为期一年的社区驱动项目，覆盖阿拉伯22个国家。数据集包括现代标准阿拉伯语(MSA)和方言阿拉伯语(DA)的指令(输入、响应对)，涵盖20个多样化主题。由44名阿拉伯世界研究者构建，他们均为本论文作者，我们的数据集提供了广泛、包容的视角。我们利用数据集评估了几款前沿LLM的文化和方言能力，揭示了显著的局限性。例如，虽然闭源LLM通常表现出色，但并非没有缺陷，小型开源模型则面临更大挑战。此外，某些国家(如埃及、阿联酋)代表度更高，而其他国家(如伊拉克、毛里塔尼亚、也门)则较低。我们公开了可复现的标注指南、代码和数据。
引用
@article{arxiv.2503.00151,
title = {Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs},
author = {Fakhraddin Alwajih and Abdellah El Mekki and Samar Mohamed Magdy and Abdelrahim A. Elmadany and Omer Nacar and El Moatez Billah Nagoudi and Reem Abdel-Salam and Hanin Atwany and Youssef Nafea and Abdulfattah Mohammed Yahya and Rahaf Alhamouri and Hamzah A. Alsayadi and Hiba Zayed and Sara Shatnawi and Serry Sibaee and Yasir Ech-Chammakhy and Walid Al-Dhabyani and Marwa Mohamed Ali and Imen Jarraya and Ahmed Oumar El-Shangiti and Aisha Alraeesi and Mohammed Anwar Al-Ghrawi and Abdulrahman S. Al-Batati and Elgizouli Mohamed and Noha Taha Elgindi and Muhammed Saeed and Houdaifa Atou and Issam Ait Yahia and Abdelhak Bouayad and Mohammed Machrouh and Amal Makouar and Dania Alkawi and Mukhtar Mohamed and Safaa Taher Abdelfadil and Amine Ziad Ounnoughene and Rouabhia Anfel and Rwaa Assi and Ahmed Sorkatti and Mohamedou Cheikh Tourad and Anis Koubaa and Ismail Berrada and Mustafa Jarrar and Shady Shehata and Muhammad Abdul-Mageed},
journal= {arXiv preprint arXiv:2503.00151},
year = {2025}
}
备注
More information about our dataset is available at our project page: https://github.com/UBC-NLP/palm