arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.03022cs.HCcs.AI
收藏

SAPIEN:由大型语言模型驱动的情感虚拟智能体

SAPIEN: Affective Virtual Agents Powered by Large Language Models

University of Rochester(罗切斯特大学)

Masum Hasan, Cengiz Ozel, Sammy Potter, Ehsan Hoque

AI总结:

本文提出 SAPIEN 平台,利用大型语言模型实现支持 13 种语言、具备情感表达和个性化设置的高保真虚拟智能体,并提供沟通反馈及多场景应用,同时审视伦理与责任使用挑战。

摘要:

在这篇演示论文中,我们介绍了 SAPIEN,这是一个由大型语言模型驱动的高保真虚拟智能体平台,能够以 13 种不同语言与用户进行开放领域对话,并通过面部表情和语音展现情绪。该平台允许用户自定义其虚拟智能体的个性、背景和对话前提,从而提供丰富、沉浸式的交互体验。此外,在虚拟会面结束后,用户可以选择对对话进行分析,并获得关于其沟通技能的可执行反馈。本文概述了该平台,并讨论了这项技术的多种应用领域,涵盖娱乐、心理健康、沟通训练、语言学习、教育、医疗保健等。同时,我们还思考了此类逼真虚拟智能体表征所涉及的伦理影响,以及在确保负责任使用方面可能面临的挑战。

英文摘要:

In this demo paper, we introduce SAPIEN, a platform for high-fidelity virtual agents driven by large language models that can hold open domain conversations with users in 13 different languages, and display emotions through facial expressions and voice. The platform allows users to customize their virtual agent's personality, background, and conversation premise, thus providing a rich, immersive interaction experience. Furthermore, after the virtual meeting, the user can choose to get the conversation analyzed and receive actionable feedback on their communication skills. This paper illustrates an overview of the platform and discusses the various application domains of this technology, ranging from entertainment to mental health, communication training, language learning, education, healthcare, and beyond. Additionally, we consider the ethical implications of such realistic virtual agent representations and the potential challenges in ensuring responsible use.

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。

↑