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：尽管当前文档摘要技术取得了巨大发展，但生成的摘要与原始文本之间仍时常出现事实不一致的问题。本研究探讨了采用提示（prompts）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（prefix-tuning）方法，该方法利用一组可训练的连续前缀提示（continuous prefix prompts）配合离散自然语言提示（discrete natural language prompts）辅助摘要生成。实验结果表明，可训练的前缀能够帮助摘要模型精确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留型摘要。生成摘要的ROUGE评分提升表明，将事实知识明确融入摘要生成过程可提升整体性能，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。