Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks
This work addresses the problem of limited interpretability and resources for Chinese hate speech detection, which is incremental but important for improving model explainability in real-world scenarios.
The authors tackled the lack of fine-grained resources and interpretability in Chinese hate speech detection by creating a span-level dataset, studying coded hate terms, and integrating a lexicon into models, resulting in significantly enhanced detection performance.
The proliferation of hate speech has inflicted significant societal harm, with its intensity and directionality closely tied to specific targets and arguments. In recent years, numerous machine learning-based methods have been developed to detect hateful comments on online platforms automatically. However, research on Chinese hate speech detection lags behind, and interpretability studies face two major challenges: first, the scarcity of span-level fine-grained annotated datasets limits models' deep semantic understanding of hate speech; second, insufficient research on identifying and interpreting coded hate speech restricts model explainability in complex real-world scenarios. To address these, we make the following contributions: (1) We introduce the Span-level Target-Aware Toxicity Extraction dataset (STATE ToxiCN), the first span-level Chinese hate speech dataset, and evaluate the hate semantic understanding of existing models using it. (2) We conduct the first comprehensive study on Chinese coded hate terms, LLMs' ability to interpret hate semantics. (3) We propose a method to integrate an annotated lexicon into models, significantly enhancing hate speech detection performance. Our work provides valuable resources and insights to advance the interpretability of Chinese hate speech detection research.