用句子级重点提示生成摘要，让长文档总结更准确可信。
Enhancing Long Document Long Form Summarisation with Self-Planning
- 用自规划识别关键内容，作为生成摘要的计划
- 在GovReport上ROUGE-L提升4.1点，SummaC得分提高35%
- 适合需要高事实一致性的长文本总结任务
我们提出一种新型长上下文摘要方法——重点提示生成，利用句子级信息作为内容计划，提升摘要的可追溯性和忠实度。该框架采用自规划方法识别重要信息，再基于计划生成摘要。我们探索了端到端和两阶段两种变体，发现两阶段流程在长且信息密集的文档上表现更优。在长文本摘要数据集上的实验表明，该方法持续提升事实一致性，同时保持相关性和整体质量。在GovReport数据集上，最佳模型的ROUGE-L提升4.1点，SummaC得分约提高35%。定性分析显示，重点提示生成有助于保留关键细节，从而在多个领域生成更准确、更具洞察力的摘要。
原文摘要 · Abstract (English)
We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the traceability and faithfulness of generated summaries. Our framework applies self-planning methods to identify important content and then generates a summary conditioned on the plan. We explore both an end-to-end and two-stage variants of the approach, finding that the two-stage pipeline performs better on long and information-dense documents. Experiments on long-form summarisation datasets demonstrate that our method consistently improves factual consistency while preserving relevance and overall quality. On GovReport, our best approach has improved ROUGE-L by 4.1 points and achieves about 35% gains in SummaC scores. Qualitative analysis shows that highlight-guided summarisation helps preserve important details, leading to more accurate and insightful summaries across domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。