@inproceedings{limisiewicz-etal-2025-dual,
    title = "Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation",
    author = "Limisiewicz, Tomasz  and
      Mare{\v{c}}ek, David  and
      Musil, Tom{\'a}{\v{s}}",
    editor = "Flek, Lucie  and
      Narayan, Shashi  and
      Phương, L{\^e} Hồng  and
      Pei, Jiahuan",
    booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
    month = oct,
    year = "2025",
    address = "Hanoi, Vietnam",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-you-zhang-rochester/2025.inlg-main.10/",
    pages = "148--164",
    abstract = "Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve their versatile capabilities, including their ability to solve language tasks and equitably represent various genders. To address these issues, we introduce Dual Dabiasing Algorithm through Model Adaptation (2DAMA). Novel Dual Debiasing enables robust reduction of stereotypical bias while preserving desired factual gender information encoded by language models. We show that 2DAMA effectively reduces gender bias in language models for English and is one of the first approaches facilitating the mitigation of their stereotypical tendencies in translation. The proposed method{'}s key advantage is the preservation of factual gender cues, which are useful in a wide range of natural language processing tasks."
}