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

arXiv: https://arxiv.org/abs/2609.29349 · HTML: https://mlsanity.com/paper/2609.29349/

## 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.

## Placed in

- LLM safety and security

## Builds on (most cited first, 15 of 15)

- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [Detecting and Understanding Harmful Memes: A Survey](https://mlsanity.com/paper/2205.04274/) (2022)
- [Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features](https://mlsanity.com/paper/2210.05916/) (2022)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [ArAIEval Shared Task: Persuasion Techniques and Disinformation Detection in Arabic Text](https://mlsanity.com/paper/2311.03179/) (2023)
- [Arabic Dataset for LLM Safeguard Evaluation](https://mlsanity.com/paper/2410.17040/) (2024)
- [The Landscape of Arabic Large Language Models (ALLMs): A New Era for Arabic Language Technology](https://mlsanity.com/paper/2506.01340/) (2025)
- [ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content](https://mlsanity.com/paper/2407.04247/) (2024)
- [MemeIntel: Explainable Detection of Propagandistic and Hateful Memes](https://mlsanity.com/paper/2502.16612/) (2025)
- [MemeLens: Multilingual Multitask VLMs for Memes](https://mlsanity.com/paper/2601.12539/) (2026)
- [FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models](https://mlsanity.com/paper/2511.18852/) (2025)
- [Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes](https://mlsanity.com/paper/2606.15307/) (2026)

## 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.