Improving Factuality of Abstractive Summarization via Contrastive Reward Learning
This work addresses the issue of factual inaccuracies in summarization for users relying on automated summaries, though it is incremental as it builds on existing reward learning and factuality metrics.
The paper tackled the problem of hallucinated or contradictory information in abstractive summarization models by proposing a contrastive learning framework that incorporates reward learning and factuality metrics, resulting in more factual summaries as confirmed by human evaluations.
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.