ArGuard is a shared task that evaluates harmful content detection in Arabic memes and LLM prompts, featuring two tracks: Track A for multimodal hate detection in memes and Track B for harmful prompt detection in Arabic LLM safety evaluation. Fifty‑eight teams registered, 35 reached the final evaluation, and 27 submitted system‑description papers, with participants experimenting with models such as AraBERT, Jais, and Qwen3‑VL. The top systems achieved macro‑F1 scores of 0.823 on A1, 0.419 on A2, 0.984 on B1, and 0.790 on B2, with fine‑grained meme classification in A2 proving the most challenging due to sparse labels and distribution shifts.
By Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Hamdy Mubarak, George Mikros, Abul Hasnat, Wajdi Zaghouani
arXiv:2608.01291v2 Announce Type: replace
Abstract: We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syri...
By Wajdi Zaghouani, Md. Rafiul Biswas, Kholoud Khalil Aldous, Mabrouka Bessghaier
arXiv:2608.21985v1 Announce Type: new
Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical...
By Fidaa Abed, Haidar Khan, M Saiful Bari, Babar Khan, Abdalghani Abujabal
Hateful memes are a growing form of multimodal online harm, where hostile intent is often conveyed through the joint interpretation of images, text, cultural references, and implicit targets. While hateful meme detection has advanced in high-resource languages, Arabic remains underexplored, with existing meme resources focusing mainly on propaganda or coarse harmful-content labels.
SZED submitted a system to the ArGuard 2026 Arabic hateful meme detection challenge, tackling both binary classification (A1) and fine‑grained multi‑label tagging (A2). For A1, the team fused MARBERTv2 and CLIP ViT‑L/14 embeddings using concatenation, self‑attention, and ensemble heads, achieving a macro‑F1 of 0.7597. For A2, they employed a multi‑task label‑attention architecture with per‑class query vectors and an auxiliary cascade‑calibration head, reaching a macro‑F1 of 0.3142 across ten active classes and analyzing per‑class error patterns and calibration effects.
By Selma Khelili, Zohra Abdeli
arXiv:2603.04410v3 Announce Type: replace-cross
Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hi...
By Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, Ihsen Alouani, Mohammed E. Fouda
The paper surveys the state of Explainable AI (XAI) in Arabic NLP, highlighting three gaps: a method gap where Arabic XAI relies mainly on limited post‑hoc techniques; a task gap with most work focused on classification tasks and little on generation, retrieval, or dialogue; and a linguistic gap where explanations rarely address Arabic‑specific phenomena such as morphology, dialects, and diglossia. It proposes a taxonomy of tasks, methods, linguistic units, and evaluation practices, and outlines a research agenda for linguistically grounded Arabic XAI.
By Salima Lamsiyah, Ruslan Mitkov
arXiv:2610.26474v2 Announce Type: replace
Abstract: Large language models (LLMs) designed to interact with users are typically trained to respond appropriately to harmful or toxic content. However, e...
By Israel Abebe Azime, Jesujoba O. Alabi, Iffat Maab, Alexander D. Cai, Tadesse Destaw Belay, Atnafu Lambebo Tonja, Jonas Kgomo, Folasade Alabi, Salomey Osei, Saminu Muhammad Aliyu, Nkechinyere Faith Aguobi, Bontu Fufa Balcha, Blessing Sibanda, Davis David, Mouhamadane Mboup, Daud Abolade, Neo Putini, Louis Powell, Kiant'e Brantley, Philipp Slusallek, Dietrich Klakow, Julia Kreutzer
The study evaluates large language models for assessing suicide risk in Arabic crisis helpline calls, comparing Arabic and English models. Using de‑identified transcripts from Lebanon’s National Lifeline, the researchers fine‑tuned instruction‑tuned LLMs and transformer encoders, achieving a macro‑F1 of 81.19 and ROC‑AUC of 90.61 for high‑risk calls in Arabic, and 85.00/92.59 in English. The results show that high‑risk calls are more distinguishable than at‑risk calls, and translating to English does not degrade performance, indicating potential for operator‑facing tools.
By Linhai Ma, Rita El Hachem, Mahatab El Hajj, Lilian Ghandour, Samah Fodeh
arXiv:2610.15795v1 Announce Type: cross
Abstract: Automated moderation systems are deployed at scale, yet they remain opaque to the users and moderators affected by their decisions, and their coverag...
By Muhammad Shahid Iqbal Malik
AraGenre 2026 is a shared task that challenges participants to perform hierarchical, definition-guided Arabic genre classification. Systems must assign each Arabic text segment both a broad communicative genre and a fine-grained specific genre, using natural-language definitions for 74 unseen specific genres in a zero-shot setting. The released datasets include limited synthetic examples for training and development, while the hidden final benchmark contains noisier, naturally occurring text across Modern Standard Arabic, Classical Arabic, and multiple dialects.
By Mo El-Haj, Saad Ezzini, Shadi Abudalfa, Mustafa Jarrar, Nguyen Minh Chi, Nguyen Minh Quan
AraGenre is a shared task on hierarchical, definition-guided Arabic genre classification, motivated by the limited availability of annotated data in Arabic and other low-resource languages. Systems as...