arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.11344cs.HCcs.CY
收藏

探索应用基于GPT-3的聊天机器人的机器人设计:Mechanical Turk的心理健康案例研究

Exploring The Design of Prompts For Applying GPT-3 based Chatbots: A Mental Wellbeing Case Study on Mechanical Turk

Harsh Kumar, Ilya Musabirov, Jiakai Shi, Adele Lauzon, Kwan Kiu Choy, Ofek Gross, Dana Kulzhabayeva, Joseph Jay Williams

摘要:

像GPT-3这样的大语言模型有可能使HCI设计人员和研究人员能够为特定应用程序创建更像人类和有用的聊天机器人。但是,评估这些聊天机器人的可行性并设计针对特定任务优化GPT-3的提示是具有挑战性的。我们提出了一个解决这些问题的案例研究,将GPT-3应用于一个简短的5分钟聊天机器人,任何人都可以更好地管理他们的情绪。我们报告了一项随机析因实验,945名参与者在Mechanical Turk上测试了三个维度的提示设计以初始化聊天机器人(身份,意图和行为),并对聊天机器人的对话和用户感知进行了定量和定性分析。我们希望其他HCI设计师和研究人员可以在此案例研究的基础上,将基于GPT-3的聊天机器人应用于特定任务,并建立和扩展我们用于提示设计和评估提示设计的方法。

英文摘要:

Large-Language Models like GPT-3 have the potential to enable HCI designers and researchers to create more human-like and helpful chatbots for specific applications. But evaluating the feasibility of these chatbots and designing prompts that optimize GPT-3 for a specific task is challenging. We present a case study in tackling these questions, applying GPT-3 to a brief 5-minute chatbot that anyone can talk to better manage their mood. We report a randomized factorial experiment with 945 participants on Mechanical Turk that tests three dimensions of prompt design to initialize the chatbot (identity, intent, and behaviour), and present both quantitative and qualitative analyses of conversations and user perceptions of the chatbot. We hope other HCI designers and researchers can build on this case study, for other applications of GPT-3 based chatbots to specific tasks, and build on and extend the methods we use for prompt design, and evaluation of the prompt design.

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。

↑