# Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes Source: [Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes]() Collection index: [llms.txt]() Data updated: 2026-05-27T05:00:05.520Z Authors: Weiming Wang, Junyu Lu, Han Wang, Xiaokun Zhang, Zewen Bai, Bo Xu, Liang Yang, Hongfei Lin Published: 2026-05-23T02:06:34.000Z ## 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 ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Harmful Meme Detection on Ex-ToxiCN-MM (test)](): Harmful Meme Detection; Ex-ToxiCN-MM (test); Accuracy: 96.7. - [Explanation Generation on Ex-ToxiCN-MM](): Explanation Generation; Ex-ToxiCN-MM; Informativeness: 3.11. ## Original sources and implementation [Original paper]() [PDF]()