Despite the great development of document summarization techniques nowadays, factual inconsistencies between the generated summaries and the original text still occur from time to time. This paper proposes a prefix-tuning-based approach that uses a set of trainable continuous prefix prompt together with discrete prompts to aid model generation, which makes a significant impact on both CNN/Daily Mail and XSum summaries generated using GPT-2. The improvements on fact preservation in the generated summaries indicates the effectiveness of adopting this prefix-tuning-based method in knowledge-enhanced document summarization, and also shows a great potential on other natural language processing tasks.

翻译：尽管当前文档摘要技术取得了长足发展，生成的摘要与原文之间仍时常出现事实不一致的问题。本文提出一种基于前缀微调的方法，通过一组可训练的连续前缀提示与离散提示相结合来辅助模型生成，该方法在利用GPT-2生成的CNN/Daily Mail和XSum摘要中均产生了显著影响。生成摘要中事实保留能力的提升，证明了这种基于前缀微调的方法在知识增强型文档摘要中的有效性，同时也展示了其在其他自然语言处理任务中的巨大潜力。