Work

Mitigating Implicit Bias in Chinese Toxic Speech Detection via Unbiased Contrastive Learning

Year: 2026

Type: article

Abstract: Mitigating human-like biases and social stereotypes in pre-trained language models (PLMs) has become a crucial task in Chinese toxic speech detection. While PLMs have achieved state-of-the-art results in mitigating explicit bias (e.g., bias on sensitive attribute words), the study of implicit bias (e.g., bias against specific demographic groups) is still under-explored. Besides, existing debiasing methods focus on the tradeoff between debiasing efficiency and model performance, while ignoring robustness against noisy data. Therefore, a debiasing method that effectively reduces biases while maintaining robustness against noisy data is needed. In this article, we propose Unbiased Contrastive Learning (UCL), which can mitigate explicit and implicit bias while maintaining robustness to noisy data. Specifically, we first analyze the bias representation problem constrained by contrastive learning objective and implement unbiased contrastive objective for learning unbiased text representations to mitigate explicit and implicit biases in Chinese toxic speech detection tasks. UCL inherits the idea of supervised contrastive learning, which encourages representations of the same sensitive attribute to be closer than those of different sensitive attributes and ensures unbiasedness by penalizing the sensitive attribute information contained in the representations. Furthermore, we design conditional normalization to reduce biased classification caused by the imbalanced distribution of demographic groups in the data. Experimental results on Chinese and English datasets show that the proposed method outperforms the state-of-the-art methods and achieves the competitive performance.

Source: ACM Transactions on Asian and Low-Resource Language Information Processing

DOI: 10.1145/3816029

Authors: Xuan Feng, Yuan Yao, Tianlong Gu, Liang Chang, Xiaoli Liu

Institution: Jinan University

Language: English

Topic: Hate Speech and Cyberbullying Detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: hybrid

Funder: National Natural Science Foundation of China