Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes

2026-05-22

AI Summary

Detecting harmful memes in Chinese is hindered by the challenges of interpreting culturally nuanced contexts and the subjectivity arising from semantic ambiguity. To address this, this work introduces Ex-ToxiCN-MM, the first Chinese multimodal meme dataset annotated with contrasting interpretations, and integrates C-HarmKB, a Chinese cultural knowledge base. The authors propose RIKE, an interpretable attribution analysis framework that combines Attribution Knowledge Enhancement (AKE) and Relative Intent Reasoning (RIR) modules to jointly leverage cultural priors and relative intent inference for harmfulness judgment. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art baselines across multiple evaluation metrics. The code, dataset, and knowledge base are publicly released to support further research.

Abstract

Research on harmful meme detection has garnered significant attention, resulting in the development of numerous datasets and methods. However, progress in detecting Chinese harmful memes lags considerably, primarily due to two challenges: first, accurately assessing a meme's harmfulness depends heavily on understanding deep cultural context; second, many memes are semantically ambiguous, making harmfulness highly subjective. To address these issues, we focus on the interpretable detection of Chinese harmful memes by constructing the first Chinese harmful meme explanation dataset, Ex-ToxiCN-MM. This dataset offers opposing interpretations, categorized as "harmful" and "non-harmful", for each meme, aiming to rigorously evaluate a model's ability to discern and comprehend ambiguous, culturally grounded content. We built a specialized knowledge base of Chinese cultural concepts and offensive vocabulary to supply models with essential prior knowledge (C-HarmKB). To address the ambiguity and lack of background knowledge in meme attribution, we have developed a comprehensive attribution analysis framework, RIKE, which includes an Attribution Knowledge Enhancement module (AKE) and a Relative Intent Reasoning module (RIR). Extensive quantitative and qualitative experiments demonstrate that our method outperforms mainstream baseline models across multiple metrics in the task of attributing harmful memes in Chinese. The code, Ex-ToxiCN-MM dataset, and Chinese Harmful Semantic Knowledge Base (C-HarmKB) involved in this study have been open-sourced at https://github.com/wimiw123/Ex-ToxiCN-MM

Problem

• harmful memes
• Chinese cultural context
• semantic ambiguity
• subjectivity
• attribution analysis

Innovation

• Chinese harmful memes
• attribution analysis
• interpretability
• cultural context
• knowledge-enhanced reasoning