"Ex-ToxiCN-MM"
Abstract
"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)."
Fields of Study & Subjects
Hate Speech and Cyberbullying Detection
Misinformation and Its Impacts
Adversarial Robustness in Machine Learning
Publication details
- Journal / source
- IEEE DataPort
- Publication date
- 13 January 2026
- Document type
- Dataset