We are happy to announce that we will be hosting 11 shared tasks
Organizers: Ahlam Bashiti (Birzeit University, Palestine), Alaa Aljabari (Birzeit University, Palestine), Mustafa Jarrar (Birzeit University, Palestine), Fadi Zaraket (Doha Institute for Graduate Studies, Qatar), Bilal Shalash (Doha Institute for Graduate Studies, Qatar), George Mikros (HBKU, Qatar), Wajdi Zaghouani (Northwestern University in Qatar, Qatar).
For more information, please visit the shared task website: https://sina.birzeit.edu/image_eval2025/index.html
Organizers: Ahmed Ali (HUMAIN, Saudi Arabia), Yassine El Kheir (DFKI, Germany), Mostafa Shahin (UNSW, Australia), Omnia Ibrahim (University of Alexandria, Egypt), Amit Meghanani (University of Sheffield), Hawau Olamide Toyin (MBZUAI, UAE), Nada AlMarwani (Taibah University, Saudi Arabia).
For more information, please visit the shared task website: coming soon.
Description: This shared task at ArabicNLP 2025 brings together three critical challenges in Arabic speech processing: Spoken Dialect Identification, Multidialectal ASR, and Diacritization Restoration. By leveraging diverse dialectal data and supporting both text-only and multimodal systems, the task aims to advance inclusive, robust, and generalizable speech technologies for the Arabic-speaking world.
Organizers: Muhammad Abdul-Mageed (University of British Columbia & MBZUAI), Bashar Talafha (University of British Columbia) Hawau Olamide Toyin (MBZUAI), Peter Sullivan (University of British Columbia), AbdelRahim Elmadany (University of British Columbia), Abdurrahman Juma (Birzeit University), Amirbek Djanibekov (MBZUAI), Chiyu Zhang (University of British Columbia), Hamad Alshehhi (MBZUAI), Hanan Aldarmaki (MBZUAI), Mustafa Jarar (Birzeit University), Nizar Habash (New York University Abu Dhabi & MBZUAI).
For more information, please visit the shared task’s website: https://nadi.dlnlp.ai/2025/
Description: MAHED 2025 is a shared task at ArabicNLP 2025, focusing on the detection of hate speech, hope speech, and emotional expression in Arabic content across both textual and multimodal formats. This task aims to advance Arabic Natural Language Processing (NLP) through multi-task model and multimodal analysis. Participants may choose to participate in one or more of the following three subtasks: (1) Text-based Hate and Hope Speech Classification, (2) Emotion, Offensive, and Directed Hate Detection (Multitask), (3) Multimodal Hateful Meme Detection.
Organizers: Wajdi Zaghouani (Northwestern University in Qatar), Md. Rafiul Biswas (Hamad Bin Khalifa University), Mabrouka Bessghaier (Northwestern University in Qatar), Shimaa Ibrahim (Northwestern University in Qatar), Firoj Alam (Qatar Computing Research Institute, HBKU).
For more information, please visit the shared task’s website: https://marsadlab.github.io/mahed2025/
Organizers: Shadi Abudalfa (KFUPM, Saudi Arabia), Saad Ezzini (KFUPM, Saudi Arabia), Ahmed Abdelali (SDAIA, Saudi Arabia), Salima Lamsiyah (Luxembourg University, Luxembourg), Hamzah Luqman (KFUPM, Saudi Arabia), Mustafa Jarrar (Birzeit University, Palestine), Mo El-Haj (VinUniversity, Vietnam), Abdelkader Elmahdaouy (Mohammed VI Polytechnic University, Morocco), Hamza Alami (USMBA, Morocco), Abdessamad Benlahbib (USMBA, Morocco), Salmane Chafik, (Mohammed VI Polytechnic University, Morocco).
For more information, please visit the shared task website: https://ezzini.github.io/AraGenEval/
Organizers: Tamer Elsayed (Qatar University, Qatar), Houda Bouamor (CMU Qatar, Qatar), Walid Massoud (Qatar University, Qatar), May Bashendy (Qatar University, Qatar), Salam Albatarni (Qatar University, Qatar), Sohaila Eltanbouly (Qatar University, Qatar).
For more information, please visit the shared task website: https://sites.google.com/view/taqeem-2025
Description: This shared task focuses on fine-grained readability classification across 19 levels using the Balanced Arabic Readability Evaluation Corpus (BAREC), a dataset of over 1 million words. Participants will build models for both sentence- and document-level classification.
Organizers: Khalid N. Elmadani (New York University Abu Dhabi), Bashar Alhafni (New York University Abu Dhab and Mohamed bin Zayed University of Artificial Intelligence), Hanada Taha-Thomure (Zayed University), and Nizar Habash (New York University Abu Dhabi).
For more information, please visit the shared task website: https://barec.camel-lab.com/sharedtask2025
Organizers: Hassan Alhuzali (Umm Al-Qura, Saudi Arabia), Ashwag Alasmari (King Khalid University, Saudi Arabia), Lama Ayash (King Khalid University, Saudi Arabia), Renad Al-Monef (King Khalid University, Saudi Arabia), Ali Alqahtani (King Khalid University, Saudi Arabia), Muhammad Abdul-Mageed (University of British Columbia (Canada) & MBZUAI (UAE)), Farah E. Shamout (NYUAD, UAE), Nizar Habash (NYUAD, UAE), Chaimae Abouzahir (NYUAD, UAE), Leen Kharouf (NYUAD, UAE), Mouath Abu-Daoud (NYUAD, UAE), Walid Al-Eisawi (NYUAD, UAE).
For more information, please visit the shared task website: https://sites.google.com/nyu.edu/arahealthqa-2025/home
Organizers: Hamdy Mubarak (Qatar Computing Research Institute), Majd Hawasly (Qatar Computing Research Institute), Walid Magdy (Qatar Computing Research Institute), Kareem Darwish (Qatar Computing Research Institute).
For more information, please visit the shared task website: coming soon.
Description: This shared task at ArabicNLP 2025 focuses on evaluating Arabic cultural understanding through two subtasks: General Culture and Islamic Culture. Using a high-quality, MCQ dataset in MSA and dialects, the task promotes the development of culturally aware models tailored to the diverse heritage of the Arab world.
Organizers: Fakhraddin Alwajih (The University of British Columbia), Abdellah EL Mekki (The University of British Columbia), Hamdy Mubarak (Qatar Computing Research Institute), Majd Hawasly (Computing Research Institute), Abubakr Mohamed (Qatar Computing Research Institute), Muhammad Abdul-Mageed (The University of British Columbia and MBZUAI).
For more information, please visit the shared task website: https://palmx.dlnlp.ai
Description: QIAS 2025 invites participants to test and advance the capabilities of Large Language Models (LLMs) in understanding and reasoning within Islamic knowledge. This shared task evaluates how well LLMs can comprehend Islamic content, solve complex problems, and accurately answer questions across diverse areas of Islamic scholarship. The challenge is structured into two focused subtasks, each consisting exclusively of multiple-choice questions (MCQs). These MCQs are organized into three levels of difficulty—beginner, intermediate, and advanced—allowing for a progressive assessment, from foundational knowledge to deep, complex reasoning.
Organizers: Abdessalam Bouchekif (HBKU University, Qatar), Mohammed Ghaly (HBKU University, Qatar), Samer Rashwani (HBKU University, Qatar), Muetaz A. Al-Khatib (HBKU University, Qatar), Emad Nawfal (Nazarbayev University, Kazakhstan), Wajdi Zaghouani (Northwestern University, Qatar),Aiman Mahmood Erbad (Qatar University, Qatar).
For more information, please visit the shared task website: https://sites.google.com/view/qias2025
August 15, 2025: Shared task papers due date
August 25, 2025: Notification of acceptance
September 5, 2025: Camera-ready papers due
November 5-9, 2025: ArabicNLP conference
All dates are 11:59 PM UTC-12h ("Anywhere on Earth")
For any questions, please contact the Shared Task Chair: arabicnlp-shared-task-chair@sigarab.org