Search papers, labs, and topics across Lattice.
This paper introduces AHA-Memes, the first large-scale benchmark for detecting hateful memes in Arabic, featuring 5,000 manually annotated examples with fine-grained, multi-label annotations that categorize various hate types. The study benchmarks multiple model architectures, including text-only, image-only, and multimodal approaches, revealing significant challenges in accurately detecting culturally nuanced hateful content. Key findings indicate that existing models struggle with the complexities of Arabic memes, underscoring the need for tailored solutions in this underexplored area of online harm.
Arabic hateful memes pose unique challenges that current detection models are ill-equipped to handle, revealing critical gaps in our understanding of online hate.
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. We introduce AHA-Memes (Arabic HAteful Memes), which is, to our knowledge, the first large-scale Arabic hateful meme benchmark with fine-grained, multi-label annotations. The dataset includes 5K manually annotated memes using a taxonomy that captures hate types, i.e., attack strategies. We further provide ~66K silver-labeled memes to support future studies. We benchmark text-only, image-only, and late-fusion multimodal models, as well as few-shot in-context learning (ICL) and open- and closed-weight Vision-Language Models (VLMs) under zero-shot and fine-tuning settings. Our results establish strong baselines and highlight key challenges in culturally grounded Arabic hateful meme detection. We release the dataset, annotation guidelines, and evaluation scripts to support future research. WARNING: This paper contains examples that may be disturbing to readers.
