用时间推理提升社交媒体时间线摘要质量
Temporal reasoning for timeline summarisation in social media
- 构建新数据集NarrativeReason，专攻事件序列的时序关系
- 通过知识蒸馏让模型同时掌握时序推理与摘要能力
- 在心理健康类长文本摘要上表现优异，适合复杂情感文本
本文探讨增强大语言模型的时间推理能力是否能提升时间线摘要质量——即对包含事件序列的长文本（如社交媒体帖子）进行摘要。我们首先提出NarrativeReason，一个专注于叙事中事件序列时序关系的新数据集，区别于以往主要关注成对事件关系的数据集。随后，我们采用知识蒸馏框架，先在时序推理任务上微调教师模型，再将知识迁移到学生模型，同时训练其完成时间线摘要任务。实验表明，该模型在跨领域心理健康相关的时间线摘要任务中表现更优，这些任务涉及带有重复事件和混合情绪的长社交媒体文本，凸显了利用时序推理提升时间线摘要的必要性与泛化能力。
原文摘要 · Abstract (English)
This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarisation, the task of summarising long texts containing sequences of events, such as social media threads. We first introduce NarrativeReason, a novel dataset focused on temporal relationships among sequential events within narratives, distinguishing it from existing temporal reasoning datasets that primarily address pair-wise event relationships. Our approach then combines temporal reasoning with timeline summarisation through a knowledge distillation framework, where we first fine-tune a teacher model on temporal reasoning tasks and then distill this knowledge into a student model while simultaneously training it for the task of timeline summarisation. Experimental results demonstrate that our model achieves superior performance on out-of-domain mental health-related timeline summarisation tasks, which involve long social media threads with repetitions of events and a mix of emotions, highlighting the importance and generalisability of leveraging temporal reasoning to improve timeline summarisation.
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。