@inproceedings{zhang-wan-2023-mil,
    title = "{MIL}-Decoding: Detoxifying Language Models at Token-Level via Multiple Instance Learning",
    author = "Zhang, Xu  and
      Wan, Xiaojun",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2023.acl-long.11/",
    doi = "10.18653/v1/2023.acl-long.11",
    pages = "190--202",
    abstract = "Despite advances in large pre-trained neural language models, they are prone to generating toxic language, which brings security risks to their applications. We introduce MIL-Decoding, which detoxifies language models at token-level by interpolating it with a trained multiple instance learning (MIL) network.MIL model is trained on a corpus with a toxicity label for each text to predict the overall toxicity and the toxicity of each token in its context. Intuitively, the MIL network computes a toxicity distribution over next tokens according to the generated context which supplements the original language model to avoid toxicity. We evaluate MIL-Decoding with automatic metrics and human evaluation, where MIL-Decoding outperforms other baselines in detoxification while it only hurts generation fluency a little bit."
}