Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Paul Roit, Johan Ferret, Lior Shani, Roee Aharoni, Geoffrey Cideron, Robert Dadashi, Matthieu Geist, Sertan Girgin
Abstract
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the generated summaries should be corroborated by their source article. In this work we leverage recent progress on textual entailment models to directly address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual-entailment rewards to optimize for factual consistency and explore the ensuing trade-offs, as improved consistency may come at the cost of less informative or more extractive summaries. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience and conciseness of the generated summaries.
BibTeX
@inproceedings{roit-etal-2023-factually,
title = "Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback",
author = "Roit, Paul and
Ferret, Johan and
Shani, Lior and
Aharoni, Roee and
Cideron, Geoffrey and
Dadashi, Robert and
Geist, Matthieu and
Girgin, Sertan and
Hussenot, Leonard and
Keller, Orgad and
Momchev, Nikola and
Ramos Garea, Sabela and
Stanczyk, Piotr and
Vieillard, Nino and
Bachem, Olivier and
Elidan, Gal and
Hassidim, Avinatan and
Pietquin, Olivier and
Szpektor, Idan",
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://aclanthology.org/2023.acl-long.344/",
doi = "10.18653/v1/2023.acl-long.344",
pages = "6252--6272"
}