超越任务型与闲聊对话：具备主动性与转换感知能力的对话智能体
Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
AI总结：
针对任务型对话与闲聊融合不足的问题，本研究提出支持双向模式切换的TACT数据集及两个新评估指标，结合DPO训练的模型在相关任务上表现优异，推动了具备主动性与转换感知能力的对话智能体研发。
摘要：
传统对话智能体要么针对任务型对话（TOD）开发，要么面向开放式闲聊设计，二者的融合研究进展有限。但真实场景中的对话自然会在这两种模式间流畅切换。为填补这一空白，我们提出TACT（TOD-And-Chitchat Transition，任务型与闲聊转换）数据集，专为转换感知对话建模设计，包含结构多样、融合度高的模式流转路径。TACT同时支持用户驱动和智能体驱动的模式切换，可实现对复杂对话动态的鲁棒建模。为评估智能体发起模式转换及从转换中恢复的能力，我们提出两个新指标——Switch（转换）和Recovery（恢复）。在TACT上训练的模型在意图检测和模式转换处理两方面均优于基线模型。此外，将直接偏好优化（DPO）应用于经TACT训练的模型可带来额外性能提升，取得75.74%的模式-意图联合准确率，且在人工评估中对比GPT-4o的胜率达70.1%。这些结果表明，将结构多样的数据与DPO相结合可提升回复质量和转换控制能力，为开发更具主动性、具备转换感知能力的对话智能体铺平道路。
英文摘要：
Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between these modes. To address this gap, we introduce TACT (TOD-And-Chitchat Transition), a dataset designed for transition-aware dialogue modeling that incorporates structurally diverse and integrated mode flows. TACT supports both user- and agent-driven mode switches, enabling robust modeling of complex conversational dynamics. To evaluate an agent's ability to initiate and recover from mode transitions, we propose two new metrics -- Switch and Recovery. Models trained on TACT outperform baselines in both intent detection and mode transition handling. Moreover, applying Direct Preference Optimization (DPO) to TACT-trained models yields additional gains, achieving 75.74\% joint mode-intent accuracy and a 70.1\% win rate against GPT-4o in human evaluation. These results demonstrate that pairing structurally diverse data with DPO enhances response quality and transition control, paving the way for more proactive and transition-aware conversational agents.
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。
