Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling

By Vidhisha Balachandran, Hannaneh Hajishirzi, William W. Cohen, Yulia Tsvetkov. 2022

61 citations recorded by the source corpus.

Abstractive summarization models often generate inconsistent summaries containing factual errors or hallucinated content. Recent works focus on correcting factual errors in generated summaries via post-editing. Such correction models are trained using adversarial non-factual summaries constructed using heuristic rules for injecting errors. However, generating non-factual summaries using heuristics often does not generalize well to actual model errors. In this work, we propose to generate hard, representative synthetic examples of non-factual summaries through infilling language models. With this data, we train a more robust fact-correction model to post-edit the summaries to improve factual consistency. Through quantitative and qualitative experiments on two popular summarization datasets— CNN/DM and XSum—we show that our approach vastly outperforms prior methods in correcting erroneous summaries. Our model—FactEdit—improves factuality scores by over ~11 points on CNN/DM and over ~31 points on XSum on average across multiple summarization models, producing more factual summaries while maintaining competitive summarization quality.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey (2022, background): “, 2020) and semi-supervised methods to correct factual errors (Cao et al., 2020; Lee et al., 2022a; Balachandran et al., 2022).”
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors (2022, unknown): “But when deployed, they still make unpredictable errors [2, 43].”
RARR: Researching and Revising What Language Models Say, Using Language Models (2022, background): “Post-hoc editing for factuality Recent work has gone beyond checking the validity of a claim to correcting a piece of text to be factually consistent with a set of evidence via post-hoc editing (Shah et al., 2020; Thorne and Vlachos, 2021; Schuster et al., 2021; Balachandran et al., 2022; Cao et al.”