让对话模型学会何时回应，提升对话自然度
From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents
- 引入时间间隔预测任务，让模型决定何时该回应
- 基于5.5万条事件驱动对话训练，性能优于现有方法
- 适合研究智能对话系统时序行为的学者和开发者
尽管对话响应生成研究多聚焦于文本上下文的连贯性，但基于时间上下文的适时回应问题仍被忽视。为此，我们提出新的任务——及时对话响应生成，并构建了TimelyChat基准，用于评估语言模型预测合适时间间隔并生成时间条件响应的能力。我们利用时间常识知识图谱中的无标签事件知识，借助大语言模型合成55,000条事件驱动对话，构建大规模训练数据集。在此基础上训练出的Timer模型可主动预测时间间隔并生成符合时间节奏的响应。实验表明，Timer在回合级与对话级评估中均优于提示型LLM和其他微调基线。数据、模型与代码已公开。
原文摘要 · Abstract (English)
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.
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。