In task-oriented dialogue, a system often needs to follow a sequence of actions, called a workflow, that complies with a set of guidelines in order to complete a task. In this paper, we propose the novel problem of multi-step workflow action prediction, in which the system predicts multiple future workflow actions. Accurate prediction of multiple steps allows for multi-turn automation, which can free up time to focus on more complex tasks. We propose three modeling approaches that are simple to implement yet lead to more action automation: 1) fine-tuning on a training dataset, 2) few-shot in-context learning leveraging retrieval and large language model prompting, and 3) zero-shot graph traversal, which aggregates historical action sequences into a graph for prediction. We show that multi-step action prediction produces features that improve accuracy on downstream dialogue tasks like predicting task success, and can increase automation of steps by 20% without requiring as much feedback from a human overseeing the system.

翻译：在任务导向型对话中，系统通常需要遵循一系列称为工作流的动作序列，这些序列需符合一套规则才能完成任务。本文提出了一个新颖问题——多步骤工作流动作预测，即系统预测多个未来工作流动作。准确预测多个步骤可实现多轮自动化，从而释放时间以专注于更复杂的任务。我们提出了三种易于实现且能提升动作自动化程度的建模方法：1）基于训练数据集进行微调；2）利用检索与大语言模型提示的少样本上下文学习；3）零样本图遍历，将历史动作序列聚合为图以进行预测。实验表明，多步骤动作预测生成的特征能提升下游对话任务（如任务成功预测）的准确性，并使步骤自动化程度提高20%，同时无需人工监督系统的频繁反馈。