Improving Factuality of Abstractive Summarization via Contrastive Reward Learning

TL;DR

This paper introduces a contrastive reward learning framework that improves the factual accuracy of abstractive summarization models by leveraging factuality metrics and feedback, resulting in more truthful summaries.

Contribution

It presents a novel contrastive reward learning approach that integrates factuality metrics into summarization training, enhancing factual correctness of generated summaries.

Findings

Summaries become more factual according to human evaluations.

Contrastive reward learning effectively incorporates factuality feedback.

Framework improves factuality without sacrificing summary quality.

Abstract

Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates recent developments in reward learning and factuality metrics. Empirical studies demonstrate that the proposed framework enables summarization models to learn from feedback of factuality metrics using contrastive reward learning, leading to more factual summaries by human evaluations. This suggests that further advances in learning and evaluation algorithms can feed directly into providing more factual summaries.