CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization

Understand

Hallucination is a known issue for neural abstractive summarization models.

• Recent work suggests that the degree of hallucination may depend on errors in the training data.
• In this work, we propose a new method called Contrastive Parameter Ensembling (CaPE) to use training data more effectively, utilizing variations in noise in training samples to reduce hallucination.
• We first select clean and noisy subsets from the training data using different automatic factual metrics.