Controllable Mixed-Initiative Dialogue Generation through Prompting

• DOI: 10.48550/arxiv.2305.04147
• Publication Date: 2023-01-01
• Authors: Maximillian Chen; Xiao Yu; Weiyan Shi; Urvi Awasthi; Yu Zhou
• Keywords: Planner; Ground truth

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular intents or strategies, prescribed a policy planner. The standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. However, supervised are limited the cost quality data annotation. We instead prompt large as drop-in replacement conditional generation. formalize construction for controllable mixed-initiative dialogue. Our findings show improvements over ground truth according human evaluation automatic metrics two tasks: PersuasionForGood Emotional Support Conversations.