Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search

Daniel King, Zejiang Shen, Nishant Subramani, Daniel S. Weld, Iz Beltagy, Doug Downey

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

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 68% on two abstractive summarization datasets, without hurting recall.

Original languageEnglish (US)
Title of host publicationGEM 2022 - 2nd Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages555-571
Number of pages17
ISBN (Electronic)9781959429128
StatePublished - 2022
Event2nd Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2022, as part of EMNLP 2022 - Abu Dhabi, United Arab Emirates
Duration: Dec 7 2022 → …

Publication series

NameGEM 2022 - 2nd Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings of the Workshop

Conference

Conference2nd Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2022, as part of EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period12/7/22 → …

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search'. Together they form a unique fingerprint.

Cite this