@inproceedings{yeo-etal-2025-understanding,
    title = "Understanding Refusal in Language Models with Sparse Autoencoders",
    author = "Yeo, Wei Jie  and
      Prakash, Nirmalendu  and
      Neo, Clement  and
      Satapathy, Ranjan  and
      Lee, Roy Ka-Wei  and
      Cambria, Erik",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.338/",
    doi = "10.18653/v1/2025.findings-emnlp.338",
    pages = "6377--6399",
    ISBN = "979-8-89176-335-7"
}