@inproceedings{gamboa-etal-2025-bias,
    title = "Bias Attribution in {F}ilipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages",
    author = "Gamboa, Lance Calvin Lim  and
      Feng, Yue  and
      Lee, Mark G.",
    editor = "Fale{\'n}ska, Agnieszka  and
      Basta, Christine  and
      Costa-juss{\`a}, Marta  and
      Sta{\'n}czak, Karolina  and
      Nozza, Debora",
    booktitle = "Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.gebnlp-1.19/",
    pages = "195--205",
    ISBN = "979-8-89176-277-0",
    abstract = "Emerging research on bias attribution and interpretability have revealed how tokens contribute to biased behavior in language models processing English texts. We build on this line of inquiry by adapting the information-theoretic bias attribution score metric for implementation on models handling agglutinative languages{---}particularly Filipino. We then demonstrate the effectiveness of our adapted method by using it on a purely Filipino model and on three multilingual models{---}one trained on languages worldwide and two on Southeast Asian data. Our results show that Filipino models are driven towards bias by words pertaining to $\textit{people}$, $\textit{objects}$, and $\textit{relationships}${---}entity-based themes that stand in contrast to the action-heavy nature of bias-contributing themes in English (i.e., $\textit{criminal}$, $\textit{sexual}$, and $\textit{prosocial}$ behaviors). These findings point to differences in how English and non-English models process inputs linked to sociodemographic groups and bias."
}