@inproceedings{zakizadeh-pilehvar-2025-gender,
    title = "Gender Encoding Patterns in Pretrained Language Model Representations",
    author = "Zakizadeh, Mahdi  and
      Pilehvar, Mohammad Taher",
    editor = "Cao, Trista  and
      Das, Anubrata  and
      Kumarage, Tharindu  and
      Wan, Yixin  and
      Krishna, Satyapriya  and
      Mehrabi, Ninareh  and
      Dhamala, Jwala  and
      Ramakrishna, Anil  and
      Galystan, Aram  and
      Kumar, Anoop  and
      Gupta, Rahul  and
      Chang, Kai-Wei",
    booktitle = "Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.trustnlp-main.31/",
    doi = "10.18653/v1/2025.trustnlp-main.31",
    pages = "489--500",
    ISBN = "979-8-89176-233-6",
    abstract = "Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges. Despite growing awareness, there is a lack of comprehensive investigation into how different models internally represent and propagate such biases. This study adopts an information-theoretic approach to analyze how gender biases are encoded within various encoder-based architectures.We focus on three key aspects: identifying how models encode gender information and biases, examining the impact of bias mitigation techniques and fine-tuning on the encoded biases and their effectiveness, and exploring how model design differences influence the encoding of biases.Through rigorous and systematic investigation, our findings reveal a consistent pattern of gender encoding across diverse models. Surprisingly, debiasing techniques often exhibit limited efficacy, sometimes inadvertently increasing the encoded bias in internal representations while reducing bias in model output distributions. This highlights a disconnect between mitigating bias in output distributions and addressing its internal representations. This work provides valuable guidance for advancing bias mitigation strategies and fostering the development of more equitable language models."
}