arXiv 2308.102782023-08-20cs.CL

CharacterChat：学习具备个性化社会支持能力的对话式AI

CharacterChat: Learning towards Conversational AI with Personalized Social Support

Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机技术研究所）；University of Electronic Science and Technology of China（电子科技大学）

Quan Tu, Chuanqi Chen, Jinpeng Li, Yanran Li, Shuo Shang, Dongyan Zhao, Ran Wang, Rui Yan

备注：: 10 pages, 6 figures, 5 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对传统情感支持对话难以适配多样化个体性格的问题，研究提出S2Conv框架，构建MBTI-1024虚拟角色库与MBTI-S2Conv数据集，开发出含性格记忆驱动对话模型和人际匹配插件的CharacterChat系统，可提供个性化社会支持且效果显著。

摘要：

在当今快节奏、互联互通的现代世界中，心理健康的重要性已成为一个极为紧迫的问题。然而，传统方法如情感支持对话（ESC）在有效应对多样化的个体性格方面面临挑战。针对这一问题，我们提出了社会支持对话（S2Conv）框架，该框架由一系列支持智能体与人际匹配机制组成，可将个体与性格适配的虚拟支持者连接起来。我们基于迈尔斯-布里格斯类型指标（MBTI）进行性格分解，构建了MBTI-1024库——一组拥有不同人设的虚拟角色。通过带有行为预设和动态记忆的改进型角色扮演提示词，我们推动构建了MBTI-S2Conv数据集，其中包含MBTI-1024库中角色之间的对话。在此基础上，我们提出了CharacterChat这一综合性S2Conv系统，它包含一个由性格和记忆驱动的对话模型，以及一个人际匹配插件模型，可从MBTI-1024库中为特定性格的个体调配最优支持者。实验结果表明，CharacterChat在提供个性化社会支持方面效果显著，同时凸显了人际匹配带来的 substantial 优势。源代码可在https://github.com/morecry/CharacterChat 获取。

英文摘要：

In our modern, fast-paced, and interconnected world, the importance of mental well-being has grown into a matter of great urgency. However, traditional methods such as Emotional Support Conversations (ESC) face challenges in effectively addressing a diverse range of individual personalities. In response, we introduce the Social Support Conversation (S2Conv) framework. It comprises a series of support agents and the interpersonal matching mechanism, linking individuals with persona-compatible virtual supporters. Utilizing persona decomposition based on the MBTI (Myers-Briggs Type Indicator), we have created the MBTI-1024 Bank, a group that of virtual characters with distinct profiles. Through improved role-playing prompts with behavior preset and dynamic memory, we facilitate the development of the MBTI-S2Conv dataset, which contains conversations between the characters in the MBTI-1024 Bank. Building upon these foundations, we present CharacterChat, a comprehensive S2Conv system, which includes a conversational model driven by personas and memories, along with an interpersonal matching plugin model that dispatches the optimal supporters from the MBTI-1024 Bank for individuals with specific personas. Empirical results indicate the remarkable efficacy of CharacterChat in providing personalized social support and highlight the substantial advantages derived from interpersonal matching. The source code is available in \url{https://github.com/morecry/CharacterChat}.

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。