#artificial intelligence
#machine learning
#computer vision
#natural language processing
Preprint
Open access
SZED at ArGuard Shared Tasks: Multi-Task Label-Attention and Cross-Modal Fusion for Arabic Hateful Meme Detection
Selma Khelili
Zohra Abdeli
Oct 2026
Artificial Intelligence
Machine Learning
Natural Language Processing
Computer Vision
Abstract
We present SZED's submission to ArGuard 2026 Track A: Arabic hateful meme detection. The task has two parts: binary classification (A1) and fine-grained multi-label tagging (A2). For A1, we fuse MARBERTv2 and CLIP ViT-L/14 embeddings, comparing concatenation, self-attention, and ensemble heads. For A2, we use a multi-task label-attention architecture with per-class query vectors and an auxiliary head for cascade calibration. We reach macro-F1 = 0.7597 on A1 and 0.3142 on A2 (averaged over 10 active classes). We report reproducibility across runs, per-class error patterns, and the effect of cascade calibration on the long-tailed A2 label space.
