@inproceedings{sun-etal-2025-debiasing,
    title = "Debiasing Static Embeddings for Hate Speech Detection",
    author = {Sun, Ling  and
      Kim, Soyoung  and
      Dong, Xiao  and
      K{\"u}bler, Sandra},
    editor = "Calabrese, Agostina  and
      de Kock, Christine  and
      Nozza, Debora  and
      Plaza-del-Arco, Flor Miriam  and
      Talat, Zeerak  and
      Vargas, Francielle",
    booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.woah-1.8/",
    pages = "67--76",
    ISBN = "979-8-89176-105-6",
    abstract = "We 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."
}