@inproceedings{van-der-poel-etal-2022-mutual,
    title = "Mutual Information Alleviates Hallucinations in Abstractive Summarization",
    author = "van der Poel, Liam  and
      Cotterell, Ryan  and
      Meister, Clara",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.emnlp-main.399/",
    doi = "10.18653/v1/2022.emnlp-main.399",
    pages = "5956--5965",
    abstract = "Despite significant progress in the quality of language generated from abstractive summarization models, these models still exhibit the tendency to hallucinate, i.e., output content not supported by the source document. A number of works have tried to fix{---}or at least uncover the source of{---}the problem with limited success. In this paper, we identify a simple criterion under which models are significantly more likely to assign more probability to hallucinated content during generation: high model uncertainty. This finding offers a potential explanation for hallucinations: models default to favoring text with high marginal probability, i.e., high-frequency occurrences in the training set, when uncertain about a continuation. It also motivates possible routes for real-time intervention during decoding to prevent such hallucinations. We propose a decoding strategy that switches to optimizing for pointwise mutual information of the source and target token{---}rather than purely the probability of the target token{---}when the model exhibits uncertainty. Experiments on the dataset show that our method decreases the probability of hallucinated tokens while maintaining the Rouge and BERT-S scores of top-performing decoding strategies."
}