Despite the great development of document summarisation techniques nowadays, factual inconsistencies between the generated summaries and the original texts still occur from time to time. This study explores the possibility of adopting prompts to incorporate factual knowledge into generated summaries. We specifically study prefix-tuning that uses a set of trainable continuous prefix prompts together with discrete natural language prompts to aid summary generation. Experimental results demonstrate that the trainable prefixes can help the summarisation model extract information from discrete prompts precisely, thus generating knowledge-preserving summaries that are factually consistent with the discrete prompts. The ROUGE improvements of the generated summaries indicate that explicitly adding factual knowledge into the summarisation process could boost the overall performance, showing great potential for applying it to other natural language processing tasks.

翻译：尽管当今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。本研究探索通过提示将事实知识融入生成摘要的可能性。我们重点研究了前缀微调技术，该技术利用可训练的连续前缀提示与离散自然语言提示共同辅助摘要生成。实验结果表明，可训练前缀能帮助摘要模型精准提取离散提示中的信息，从而生成与离散提示在事实上保持一致的"知识保持型"摘要。摘要的ROUGE指标提升表明，将事实知识显式加入摘要生成过程可显著提升整体性能，这为将该方法应用于其他自然语言处理任务展现了巨大潜力。