让对话系统理解核心与细节事件关系，生成更自然回应。
EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems
- 构建动态事件图，区分核心与支持性事件
- 三种事件关系建模，提升上下文理解精度
- 适合需要精准语境把握的对话任务
大语言模型虽提升了对话系统性能，但常孤立处理对话轮次，忽略引导自然互动的事件结构。为此，我们提出EventWeave框架，显式建模对话事件间关系，生成更具上下文相关性的回复。该框架构建动态事件图，区分核心事件（主要目标）与支持事件（关联细节），采用多头注意力机制选择当前轮次最相关的事件。不同于摘要或标准图方法，本方法捕捉三类事件关系，实现更精细的上下文建模。在三个对话数据集上的实验表明，EventWeave生成的回复更自然、上下文相关性更强，且计算开销低于处理完整历史的模型。消融实验证明性能提升源于更优的事件关系建模，而非信息密度增加。该方法通过定向优化技术，在不同对话长度下均保持强性能，平衡了全面理解与简洁回应。
原文摘要 · Abstract (English)
Large language models have improved dialogue systems, but often process conversational turns in isolation, overlooking the event structures that guide natural interactions. Hence we introduce EventWeave, a framework that explicitly models relationships between conversational events to generate more contextually appropriate dialogue responses. EventWeave constructs a dynamic event graph that distinguishes between core events (main goals) and supporting events (interconnected details), employing a multi-head attention mechanism to selectively determine which events are most relevant to the current turn. Unlike summarization or standard graph-based approaches, our method captures three distinct relationship types between events, allowing for more nuanced context modeling. Experiments on three dialogue datasets demonstrate that EventWeave produces more natural and contextually appropriate responses while requiring less computational overhead than models processing the entire dialogue history. Ablation studies confirm improvements stem from better event relationship modeling rather than increased information density. Our approach effectively balances comprehensive context understanding with generating concise responses, maintaining strong performance across various dialogue lengths through targeted optimization techniques.
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。