MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
This addresses the challenge of automated harmful meme detection for social media platforms, though it is incremental as it builds on existing multimodal detection research.
The authors tackled the problem of detecting harmful memes by introducing MemeMind, a large-scale multimodal dataset with Chain-of-Thought reasoning annotations, and MemeGuard, a detection framework that outperformed state-of-the-art methods in experiments.
The rapid development of social media has intensified the spread of harmful content. Harmful memes, which integrate both images and text, pose significant challenges for automated detection due to their implicit semantics and complex multimodal interactions. Although existing research has made progress in detection accuracy and interpretability, the lack of a systematic, large-scale, diverse, and highly explainable dataset continues to hinder further advancement in this field. To address this gap, we introduce MemeMind, a novel dataset featuring scientifically rigorous standards, large scale, diversity, bilingual support (Chinese and English), and detailed Chain-of-Thought (CoT) annotations. MemeMind fills critical gaps in current datasets by offering comprehensive labeling and explicit reasoning traces, thereby providing a solid foundation for enhancing harmful meme detection. In addition, we propose an innovative detection framework, MemeGuard, which effectively integrates multimodal information with reasoning process modeling, significantly improving models' ability to understand and identify harmful memes. Extensive experiments conducted on the MemeMind dataset demonstrate that MemeGuard consistently outperforms existing state-of-the-art methods in harmful meme detection tasks.