@inproceedings{yang-etal-2025-dpo,
    title = "How Does {DPO} Reduce Toxicity? A Mechanistic Neuron-Level Analysis",
    author = "Yang, Yushi  and
      Sondej, Filip  and
      Mayne, Harry  and
      Lee, Andrew  and
      Mahdi, Adam",
    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.1501/",
    pages = "29512--29531",
    ISBN = "979-8-89176-332-6"
}