Faithfulness-Aware Decoding Strategies for Abstractive Summarization

David Wan, Mengwen Liu, Kathleen McKeown, Markus Dreyer, Mohit Bansal


Abstract
Despite significant progress in understanding and improving faithfulness in abstractive summarization, the question of how decoding strategies affect faithfulness is less studied. We present a systematic study of the effect of generation techniques such as beam search and nucleus sampling on faithfulness in abstractive summarization. We find a consistent trend where beam search with large beam sizes produces the most faithful summaries while nucleus sampling generates the least faithful ones. We propose two faithfulness-aware generation methods to further improve faithfulness over current generation techniques: (1) ranking candidates generated by beam search using automatic faithfulness metrics and (2) incorporating lookahead heuristics that produce a faithfulness score on the future summary. We show that both generation methods significantly improve faithfulness across two datasets as evaluated by four automatic faithfulness metrics and human evaluation. To reduce computational cost, we demonstrate a simple distillation approach that allows the model to generate faithful summaries with just greedy decoding.
Anthology ID:
2023.eacl-main.210
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2864–2880
Language:
URL:
https://aclanthology.org/2023.eacl-main.210
DOI:
10.18653/v1/2023.eacl-main.210
Bibkey:
Cite (ACL):
David Wan, Mengwen Liu, Kathleen McKeown, Markus Dreyer, and Mohit Bansal. 2023. Faithfulness-Aware Decoding Strategies for Abstractive Summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2864–2880, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Faithfulness-Aware Decoding Strategies for Abstractive Summarization (Wan et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.210.pdf
Video:
 https://aclanthology.org/2023.eacl-main.210.mp4