aiqbench analysis
This paper introduces AHA-Memes, the first large-scale benchmark for detecting hate speech in Arabic memes through fine-grained multimodal analysis. By evaluating various Vision-Language Models on this culturally grounded dataset, it establishes critical baselines and highlights specific challenges in interpreting implicit hostility within high-resource language contexts. The release of these annotations provides essential infrastructure for advancing safety research in underrepresented linguistic domains.
AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes
arXiv:2607.27393v1 Announce Type: new Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2607.27393 [cs.CL]
(or arXiv:2607.27393v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.27393 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 266 words
Related coverage
Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes
arXiv · Jun 17, 2026
SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes
arXiv · Jul 28, 2026
ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts
arXiv · Sep 25, 2026
MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal Models
arXiv · Sep 3, 2026