让新闻时间线只聚焦特定事件，用自省机制提升相关性。
Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
- 用大模型按约束条件筛选新闻并聚类关键事件
- 自反思机制使生成时间线相关性提升明显
- 适合需要定制化事件回顾的读者或研究者
针对公众人物或组织的新闻文章，时间线摘要（TLS）旨在生成其关键事件的时间序列。但传统任务定义模糊，不同读者关注点各异，不存在唯一最优时间线。本文提出新任务——受限时间线摘要（CTLS），要求时间线中所有事件均满足特定约束。例如，仅包含泰格·伍兹法律纠纷相关的事件。我们构建了包含47个实体、每实体5种约束的真人验证数据集。提出一种基于大语言模型（LLM）的方法，在摘要生成时引入自反思机制，通过聚类识别关键事件，显著提升生成结果的相关性。
原文摘要 · Abstract (English)
Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too underspecified, since what is of interest to each reader may vary, and hence there is not a single ideal or optimal timeline. In this paper, we introduce a novel task, called Constrained Timeline Summarization (CTLS), where a timeline is generated in which all events in the timeline meet some constraint. An example of a constrained timeline concerns the legal battles of Tiger Woods, where only events related to his legal problems are selected to appear in the timeline. We collected a new human-verified dataset of constrained timelines involving 47 entities and 5 constraints per entity. We propose an approach that employs a large language model (LLM) to summarize news articles according to a specified constraint and cluster them to identify key events to include in a constrained timeline. In addition, we propose a novel self-reflection method during summary generation, demonstrating that this approach successfully leads to improved performance.
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。