Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Challenges in Automated Debiasing for Toxic Language Detection

About

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.

Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Noah A. Smith, Yejin Choi• 2021

Related benchmarks

TaskDatasetResultRank
Hate Speech DetectionMHS
Accuracy80.79
19
Hate Speech DetectionPOPQUORN
Accuracy74.38
19
Showing 2 of 2 rows

Other info

Follow for update