Debiasing Static Embeddings for Hate Speech Detection

AbstractWe examine how embedding bias affects hate speech detection by evaluating two debiasing methods—hard-debiasing and soft-debiasing. We analyze stereotype and sentiment associations within the embedding space and assess whether debiased models reduce censorship of marginalized authors while improving detection of hate speech targeting these groups. Our findings highlight how embedding bias propagates into downstream tasks and demonstrates how well different embedding bias metrics can predict bias in hate speech detection.