Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
This addresses the issue of factual inaccuracies in summarization for users relying on automated systems, representing an incremental improvement over existing methods.
The paper tackled the problem of factually inconsistent text generation in abstractive summarization by using reinforcement learning with textual entailment rewards, resulting in improved faithfulness, salience, and conciseness of summaries as shown by automatic metrics and human evaluation.
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.