MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gu, Hexiang, Yu, Qifan, Liu, Yuan, Li, Zikang, Hou, Saihui, Zhao, Jian, He, Zhaofeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911559036436480
author Gu, Hexiang
Yu, Qifan
Liu, Yuan
Li, Zikang
Hou, Saihui
Zhao, Jian
He, Zhaofeng
author_facet Gu, Hexiang
Yu, Qifan
Liu, Yuan
Li, Zikang
Hou, Saihui
Zhao, Jian
He, Zhaofeng
contents As a multimodal medium combining images and text, memes frequently convey implicit harmful content through metaphors and humor, rendering the detection of harmful memes a complex and challenging task. Although recent studies have made progress in detection accuracy and interpretability, large-scale, high-quality datasets for harmful memes remain scarce, and current methods still struggle to capture implicit risks and nuanced semantics. Thus, we construct MemeMind, a large-scale harmful meme dataset. Aligned with the international standards and the context of internet, MemeMind provides detailed Chain-of-Thought (CoT) reasoning annotations to support fine-grained analysis of implicit intentions in memes. Based on this dataset, we further propose MemeGuard, a reasoning-oriented multimodal detection framework that significantly improves both the accuracy of harmful meme detection and the interpretability of model decisions. Extensive experimental results demonstrate that MemeGuard outperforms existing state-of-the-art methods on the MemeMind dataset, establishing a solid foundation for future research in harmful meme detection. The complete dataset and code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18919
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
Gu, Hexiang
Yu, Qifan
Liu, Yuan
Li, Zikang
Hou, Saihui
Zhao, Jian
He, Zhaofeng
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
As a multimodal medium combining images and text, memes frequently convey implicit harmful content through metaphors and humor, rendering the detection of harmful memes a complex and challenging task. Although recent studies have made progress in detection accuracy and interpretability, large-scale, high-quality datasets for harmful memes remain scarce, and current methods still struggle to capture implicit risks and nuanced semantics. Thus, we construct MemeMind, a large-scale harmful meme dataset. Aligned with the international standards and the context of internet, MemeMind provides detailed Chain-of-Thought (CoT) reasoning annotations to support fine-grained analysis of implicit intentions in memes. Based on this dataset, we further propose MemeGuard, a reasoning-oriented multimodal detection framework that significantly improves both the accuracy of harmful meme detection and the interpretability of model decisions. Extensive experimental results demonstrate that MemeGuard outperforms existing state-of-the-art methods on the MemeMind dataset, establishing a solid foundation for future research in harmful meme detection. The complete dataset and code will be released upon acceptance.
title MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.18919