Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Existing meme research is distributed across tasks (e.g., hate, misogyny, propaganda, sentiment, humour) and languages, which limits cross-domain generalization. To address this gap, we propose MemeLens, a unified multilingual, multitask explanation-enhanced Vision-Language Model (VLM) for meme understanding. We consolidate 38 public meme datasets, filter and map dataset-specific labels into a shared taxonomy of 20 tasks spanning harm, targets, figurative/pragmatic intent, and affect. We present a comprehensive empirical analysis across modeling paradigms, task categories, and datasets. Our findings suggest that robust meme understanding requires multimodal training, varies substantially across semantic categories, and remains sensitive to over-specialization when models are fine-tuned on individual datasets rather than trained in a unified setting. We make the experimental resources (Code: https://github.com/MohamedBayan/MemeLens | MemeLens-VLM: https://huggingface.co/QCRI/MemeLens-VLM | MemeLens-Datasets: https://huggingface.co/datasets/QCRI/MemeLens) publicly available to the community.

Harmful content appears in diverse forms, ranging from multimodal memes targeting protected groups to textual prompts designed to elicit unsafe responses from large language models. However, existing Arabic resources typically study these settings separately and often rely on coarse-grained labels. We introduce ArGuard, a shared task on harmful content detection in Arabic memes and LLM prompts. ArGuard consists of two tracks: Track A focuses on multimodal hate detection in Arabic memes, while Track B addresses harmful prompt detection for Arabic LLM safety evaluation. Overall, 58 teams registered for the shared task, 35 participated in the final evaluation phase, and 27 submitted system-description papers. Participating systems explored a range of approaches, including fine-tuning encoder- and decoder-based models such as AraBERT, Jais, and Qwen3-VL. The best-performing systems achieved macro-F1 scores of 0.823 on Subtask A1, 0.419 on Subtask A2, 0.984 on Subtask B1, and 0.790 on Subtask B2. These results highlight fine-grained meme classification (Subtask A2) as the most challenging setting, partly due to sparse labels and train-test distribution shifts. To facilitate further research on Arabic harmful-content detection, we release the task datasets and associated resources through the shared-task website.

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, which is, to our knowledge, the first large 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.

Misinformation on social media undermines informed decision-making and public trust. Prebunking offers a proactive complement by helping users recognize manipulation tactics before they encounter them in the wild. We present CritiSense, a mobile media-literacy app that builds these skills through short, interactive challenges with instant feedback. It is the first multilingual (supporting nine languages) and modular platform, designed for rapid updates across topics and domains. We report a usability study with 93 users: 83.9% expressed overall satisfaction and 90.1% rated the app as easy to use. Qualitative feedback indicates that CritiSense helps improve digital literacy skills. Overall, it provides a multilingual prebunking platform and a testbed for measuring the impact of microlearning on misinformation resilience. Over 6 months, we have reached 500+ active users. It is freely available on the Apple App Store and Google [Play Store](https://play.google.com/store/apps/details?id=com.critisense hl=en).

The proliferation of multimodal content on social media presents significant challenges in understanding and moderating complex, context-dependent issues such as misinformation, hate speech, and propaganda. While efforts have been made to develop resources and propose new methods for automatic detection, limited attention has been given to label detection and the generation of explanation-based rationales for predicted labels. To address this challenge, we introduce MemeXplain, an explanation-enhanced dataset for propaganda memes in Arabic and hateful memes in English, making it the first large-scale resource for these tasks. To solve these tasks, we propose a novel multi-stage optimization approach and train Vision-Language Models (VLMs). Our results demonstrate that this approach significantly improves performance over the base model for both label detection and explanation generation, outperforming the current state-of-the-art with an absolute improvement of approximately 3% on ArMeme and 7% on Hateful Memes. For reproducibility and future research, we aim to make the MemeXplain dataset and scripts publicly available.

This paper presents the MAHED 2025 Shared Task on Multimodal Detection of Hope and Hate Emotions in Arabic Content, comprising three subtasks: (1) text-based classification of Arabic content into hate and hope, (2) multi-task learning for joint prediction of emotions, offensive content, and hate speech, and (3) multimodal detection of hateful content in Arabic memes. We provide three high-quality datasets totaling over 22,000 instances sourced from social media platforms, annotated by native Arabic speakers with Cohen’s Kappa exceeding 0.85. Our evaluation attracted 46 leaderboard submissions from participants, with systems leveraging Arabic-specific pre-trained language models (AraBERT, MARBERT), large language models (GPT-4, Gemini), and multimodal fusion architectures combining CLIP vision encoders with Arabic text models. The best-performing systems achieved macro F1-scores of 0.723 (Task 1), 0.578 (Task 2), and 0.796 (Task 3), with top teams employing ensemble methods, class-weighted training, and OCR-aware multimodal fusion. Analysis reveals persistent challenges in dialectal robustness, minority class detection for hope speech, and highlights key directions for future Arabic content moderation research.

The automatic identification of misleading and persuasive content has emerged as a significant issue among various stakeholders, including social media platforms, policymakers, and the broader society. To tackle this issue within the context of memes, we organized a shared task at SemEval-2024, focusing on the multilingual detection of persuasion techniques. This paper outlines the dataset, the organization of the task, the evaluation framework, the outcomes, and the systems that participated. The task targets memes in four languages, with the inclusion of three surprise test datasets in Bulgarian, North Macedonian, and Arabic. It encompasses three subtasks: (i) identifying whether a meme utilizes a persuasion technique; (ii) identifying persuasion techniques within the meme’s ”textual content”; and (iii) identifying persuasion techniques across both the textual and visual components of the meme (a multimodal task). Furthermore, due to the complex nature of persuasion techniques, we present a hierarchy that groups the 22 persuasion techniques into several levels of categories. This became one of the attractive shared tasks in SemEval 2024, with 153 teams registered, 48 teams submitting results, and finally, 32 system description papers submitted.

With the rise of digital communication memes have become a significant medium for cultural and political expression that is often used to mislead audience. Identification of such misleading and persuasive multimodal content become more important among various stakeholders, including social media platforms, policymakers, and the broader society as they often cause harm to the individuals, organizations and/or society. While there has been effort to develop AI based automatic system for resource rich languages (e.g., English), it is relatively little to none for medium to low resource languages. In this study, we focused on developing an Arabic memes dataset with manual annotations of propagandistic content. We annotated ∼6K Arabic memes collected from various social media platforms, which is a first resource for Arabic multimodal research. We provide a comprehensive analysis aiming to develop computational tools for their detection. We made the dataset publicly available for the community.