@inproceedings{qian-etal-2025-disentangling,
    title = "Disentangling Biased Representations: A Causal Intervention Framework for Fairer {NLP} Models",
    author = "Qian, Yangge  and
      Hu, Yilong  and
      Zhang, Siqi  and
      Gu, Xu  and
      Qin, Xiaolin",
    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/ingest-emnlp/2025.gebnlp-1.33/",
    doi = "10.18653/v1/2025.gebnlp-1.33",
    pages = "393--402",
    ISBN = "979-8-89176-277-0",
    abstract = "Natural language processing (NLP) systems often inadvertently encode and amplify social biases through entangled representations of demographic attributes and task-related attributes. To mitigate this, we propose a novel framework that combines causal analysis with practical intervention strategies. The method leverages attribute-specific prompting to isolate sensitive attributes while applying information-theoretic constraints to minimize spurious correlations. Experiments across six language models and two classification tasks demonstrate its effectiveness. We hope this work will provide the NLP community with a causal disentanglement perspective for achieving fairness in NLP systems."
}