During task-oriented dialogues (TODs), human users naturally introduce chitchat that is beyond the immediate scope of the task, interfering with the flow of the conversation. To address this issue without the need for expensive manual data creation, we use few-shot prompting with Llama-2-70B to enhance the MultiWOZ dataset with user backstories, a typical example of chitchat interference in TODs. We assess the impact of this addition by testing two models: one trained solely on TODs and another trained on TODs with a preliminary chitchat interaction. Our analysis demonstrates that our enhanced dataset poses a challenge for these systems. Moreover, we demonstrate that our dataset can be effectively used for training purposes, enabling a system to consistently acknowledge the user's backstory while also successfully moving the task forward in the same turn, as confirmed by human evaluation. These findings highlight the benefits of generating novel chitchat-TOD scenarios to test TOD systems more thoroughly and improve their resilience to natural user interferences

翻译：在任务导向对话（TODs）中，用户常会自然地引入超出当前任务范围的闲聊内容，从而干扰对话的流畅性。为解决此问题，同时避免昂贵的人工数据创建，我们采用Llama-2-70B进行少样本提示，为MultiWOZ数据集增添了用户背景故事——这是TOD中闲聊干扰的一个典型示例。我们通过测试两种模型来评估这一添加的影响：一种仅使用TOD数据训练，另一种则在TOD数据基础上加入了初步的闲聊互动训练。分析表明，我们增强的数据集对这些系统构成了挑战。此外，我们证明该数据集可有效用于训练，使系统能够在同一轮对话中既持续回应用户的背景故事，又成功推动任务进展，这一点已通过人工评估得到证实。这些发现凸显了生成新颖的闲聊-TOD场景的益处，既可更全面地测试TOD系统，又能提升其对自然用户干扰的鲁棒性。