@inproceedings{liu-etal-2024-intrinsic,
    title = "Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis",
    author = "Liu, Guangliang  and
      Mao, Haitao  and
      Tang, Jiliang  and
      Johnson, Kristen",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.918/",
    doi = "10.18653/v1/2024.emnlp-main.918",
    pages = "16439--16455"
}