Call for Participation: ArGuard 2026 Shared Task at ArabicNLP 2026
We invite researchers and practitioners to participate in ArGuard 2026: Harmful Content Detection in Arabic Memes and LLM Prompts, a shared task organized as part of ArabicNLP 2026, co-located with EMNLP 2026.
ArGuard 2026 focuses on Arabic-specific challenges in harmful content detection, including dialectal variation, sarcasm, cultural references, code-switching, multimodal signals, and implicit harmful intent.
Tracks
- Track A: Multimodal Hateful Meme Detection
- Track B: Harmful Prompt Detection for LLMs
Participants are invited to develop systems, submit predictions, and write system description papers for the ArabicNLP 2026 proceedings.
Important Dates
- August 1, 2026: Registration deadline and test set release
- August 6, 2026: Evaluation deadline
- August 8, 2026: Leaderboard release
- August 18, 2026: Shared task papers due
- August 30, 2026: Notification of acceptance
- September 10, 2026: Camera-ready papers due
- October 24–29, 2026: ArabicNLP 2026 Conference
Links
- Website: https://araieval.github.io/ArGuard2026/
- Data and code: https://github.com/araieval/ArGuard-2026-tasks
We encourage participation from the NLP, multimodal AI, online safety, LLM safety, and Arabic language technology communities.