English

Challenges in Automated Debiasing for Toxic Language Detection

Computation and Language 2021-02-02 v1

Abstract

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English). Our comprehensive experiments establish that existing methods are limited in their ability to prevent biased behavior in current toxicity detectors. We then propose an automatic, dialect-aware data correction method, as a proof-of-concept. Despite the use of synthetic labels, this method reduces dialectal associations with toxicity. Overall, our findings show that debiasing a model trained on biased toxic language data is not as effective as simply relabeling the data to remove existing biases.

Keywords

Cite

@article{arxiv.2102.00086,
  title  = {Challenges in Automated Debiasing for Toxic Language Detection},
  author = {Xuhui Zhou and Maarten Sap and Swabha Swayamdipta and Noah A. Smith and Yejin Choi},
  journal= {arXiv preprint arXiv:2102.00086},
  year   = {2021}
}

Comments

EACL 2021

R2 v1 2026-06-23T22:40:20.347Z