通过提示实现可控的混合主动对话生成
Controllable Mixed-Initiative Dialogue Generation through Prompting
AI总结：
针对混合主动对话中可控生成受限于标注成本的问题，提出用提示大型语言模型替代微调，形式化提示构建，在PersuasionForGood和情感支持对话任务上经人类评估和自动指标优于微调及真实响应。
摘要：
混合主动对话任务涉及信息和对话控制的反复交换。对话代理通过生成遵循特定对话意图或策略的响应来获得控制权，这些意图或策略由策略规划器规定。标准方法是微调预训练语言模型，以在这些意图条件下执行生成。然而，这些有监督的生成模型受到数据标注成本和质量的限制。我们转而提示大型语言模型，作为微调在条件生成上的直接替代。我们形式化了可控混合主动对话的提示构建。我们的研究结果显示，在人类评估和自动指标上，对于两个任务：PersuasionForGood和情感支持对话，我们的方法优于微调和真实响应。
英文摘要：
Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. The standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. However, these supervised generation models are limited by the cost and quality of data annotation. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation. We formalize prompt construction for controllable mixed-initiative dialogue. Our findings show improvements over fine-tuning and ground truth responses according to human evaluation and automatic metrics for two tasks: PersuasionForGood and Emotional Support Conversations.
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。
