@inproceedings{goyal-etal-2025-breaking,
    title = "Breaking Bad Tokens: Detoxification of {LLM}s Using Sparse Autoencoders",
    author = "Goyal, Agam  and
      Rathi, Vedant  and
      Yeh, William  and
      Wang, Yian  and
      Chen, Yuen  and
      Sundaram, Hari",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.641/",
    pages = "12702--12720",
    ISBN = "979-8-89176-332-6"
}