从回应什么到何时回应：面向开放域对话智能体的适时回应生成
From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents
AI总结：
针对开放域对话回应时机研究不足的问题，该研究提出适时对话回应生成任务与TimelyChat基准，构建5.5万条事件驱动对话数据集并训练对话智能体Timer，其表现优于现有基线。
摘要：
对话回应生成研究主要聚焦于基于文本上下文生成连贯回应，但基于时间上下文确定回应时机这一关键问题仍未得到充分探索。为填补这一空白，我们提出了“适时对话回应生成”这一新任务，并推出TimelyChat基准，用于评估语言模型预测合理时间间隔并生成受时间约束的回应的能力。此外，我们利用时间常识知识图谱中的无标注事件知识，借助大语言模型（LLM）合成了5.5万条事件驱动型对话，构建了一个大规模训练数据集。随后我们训练了对话智能体Timer，它能够主动预测时间间隔，并生成与这些时间间隔相匹配的适时回应。实验结果表明，在轮次级和对话级评估中，Timer的表现均优于基于提示的大语言模型及其他微调基线模型。我们公开发布了相关数据、模型和代码。
英文摘要：
While research on dialogue response generation has primarily focused on generating coherent responses conditioning on textual context, the critical question of when to respond grounded on the temporal context remains underexplored. To bridge this gap, we propose a novel task called timely dialogue response generation and introduce the TimelyChat benchmark, which evaluates the capabilities of language models to predict appropriate time intervals and generate time-conditioned responses. Additionally, we construct a large-scale training dataset by leveraging unlabeled event knowledge from a temporal commonsense knowledge graph and employing a large language model (LLM) to synthesize 55K event-driven dialogues. We then train Timer, a dialogue agent designed to proactively predict time intervals and generate timely responses that align with those intervals. Experimental results show that Timer outperforms prompting-based LLMs and other fine-tuned baselines in both turn-level and dialogue-level evaluations. We publicly release our data, model, and code.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
