%0 Conference Proceedings %T Don’t Say What You Don’t Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search %A King, Daniel %A Shen, Zejiang %A Subramani, Nishant %A Weld, Daniel S. %A Beltagy, Iz %A Downey, Doug %Y Bosselut, Antoine %Y Chandu, Khyathi %Y Dhole, Kaustubh %Y Gangal, Varun %Y Gehrmann, Sebastian %Y Jernite, Yacine %Y Novikova, Jekaterina %Y Perez-Beltrachini, Laura %S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM) %D 2022 %8 December %I Association for Computational Linguistics %C Abu Dhabi, United Arab Emirates (Hybrid) %F king-etal-2022-dont %X Abstractive summarization systems today produce fluent and relevant output, but often “hallucinate” statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that models hallucinate because they train on target summaries that are unsupported by the source. Based on our findings, we present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations. Given the model states and outputs at a given step, PINOCCHIO detects likely model hallucinations based on various measures of attribution to the source text. PINOCCHIO backtracks to find more consistent output, and can opt to produce no summary at all when no consistent generation can be found. In experiments, we find that PINOCCHIO improves the consistency of generation by an average of 67% on two abstractive summarization datasets, without hurting recall. %R 10.18653/v1/2022.gem-1.51 %U https://aclanthology.org/2022.gem-1.51 %U https://doi.org/10.18653/v1/2022.gem-1.51 %P 555-571