构建可主动切换对话模式的智能助手，提升真实场景聊天流畅度。
Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
- 设计新数据集TACT，支持用户与机器人双向模式切换
- 提出切换与恢复双指标，模型在转换任务上准确率达75.74%
- 结合DPO优化后，人评胜率超GPT-4o达70.1%
对话系统传统上分为任务导向与闲聊两类，但现实对话常在这两种模式间自然流转。为填补这一空白，我们提出TACT（TOD-And-Chitchat Transition）数据集，支持用户和代理驱动的模式切换，涵盖结构多样的融合对话流。为此，我们设计了两个新评估指标——切换（Switch）与恢复（Recovery），用于衡量代理发起与应对模式转换的能力。在TACT上训练的模型在意图识别与模式转换处理上均优于基线。进一步应用直接偏好优化（DPO）后，模型达到75.74%的联合模式-意图准确率，并在人类评估中以70.1%胜率超越GPT-4o。结果表明，结构多样数据与DPO结合能显著提升响应质量与转换控制能力，推动更主动、更适应过渡的对话智能体发展。
原文摘要 · Abstract (English)
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.
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。