Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks

TL;DR

This paper introduces a new span-level dataset for Chinese hate speech, studies coded hate terms, and proposes an improved detection method integrating lexicons to enhance interpretability and performance.

Contribution

It provides the first span-level Chinese hate speech dataset, analyzes coded hate terms, and develops a lexicon-integrated detection framework for better interpretability.

Findings

The STATE ToxiCN dataset enables detailed hate speech analysis.

LLMs can interpret coded hate terms with varying success.

Lexicon integration improves detection accuracy significantly.

Abstract

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.