mlsanityData to 14 Oct 2026

ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts

arXiv 2609.29349 ↗First posted 24 Sep 2026cs.CL cs.AIcited by 0

New in LLM safety and security; no direction yet. LLM safety and security

Abstract (arXiv)

ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate detection in Arabic memes, while Track B addresses harmful prompt detection for Arabic LLM safety evaluation. In total, 58 teams registered, 35 participated in the final evaluation, and 27 submitted system-description papers. Participating teams explored models such as AraBERT, Jais, and Qwen3-VL. The best systems achieved macro-F1 scores of 0.823 on A1, 0.419 on A2, 0.984 on B1, and 0.790 on B2. Fine-grained meme classification in A2 was the most challenging setting, partly due to sparse labels and train-test distribution shifts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 46 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

15 of 46 references.

References · 15

  1. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  2. 2024WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMscited by 496
  3. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 490
  4. 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
  5. 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
  6. 2022Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Featurescited by 56
  7. 2025The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating Itcited by 45
  8. 2023ArAIEval Shared Task: Persuasion Techniques and Disinformation Detection in Arabic Textcited by 19
  9. 2024Arabic Dataset for LLM Safeguard Evaluationcited by 17
  10. 2025The Landscape of Arabic Large Language Models (ALLMs): A New Era for Arabic Language Technologycited by 12
  11. 2024ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Contentcited by 11
  12. 2025MemeIntel: Explainable Detection of Propagandistic and Hateful Memescited by 10
3 more
  1. 2026MemeLens: Multilingual Multitask VLMs for Memescited by 6
  2. 2025FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Modelscited by 5
  3. 2026Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes
  2. 2024MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention
  3. 2025LLM-based Semantic Augmentation for Harmful Content Detection
  4. 2025From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment
  5. 2026Redteaming Leading Arabic LLMs with ASAS
  6. 2023Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models
  7. 2025BingoGuard: LLM Content Moderation Tools with Risk Levels
  8. 2026Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation