arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.18921cs.CL

捕捉心智,而不仅仅是语言:利用性格指示数据增强角色扮演语言模型

Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data

School of Data Science, Fudan University(复旦大学数据科学学院);School of Computer Science, Fudan University(复旦大学计算机科学技术学院)

Yiting Ran, Xintao Wang, Rui Xu, Xinfeng Yuan, Jiaqing Liang, Deqing Yang, Yanghua Xiao

AI总结:

本文提出利用心理量表问题蒸馏高级RPA生成性格指示数据,以增强小型角色扮演语言模型对角色心智的捕捉,实验证明该方法显著提升了模型的通用与性格相关角色扮演能力。

摘要:

角色扮演智能体(RPA)是大语言模型(LLM)的热门应用领域,吸引了工业界和学术界的极大兴趣。虽然现有的RPA能很好地描绘角色的知识和语气,但它们在捕捉心智方面面临挑战,尤其是对于小型角色扮演语言模型(RPLM)。在本文中,我们提出通过性格指示数据来增强RPLM。具体而言,我们利用心理量表中的问题,并蒸馏高级RPA来生成把握角色心智的对话。实验结果验证了,使用我们的数据集训练的RPLM在通用和性格相关评估中均展现出高级的角色扮演能力。代码和数据可在该URL获取。

英文摘要:

Role-playing agents (RPA) have been a popular application area for large language models (LLMs), attracting significant interest from both industry and academia.While existing RPAs well portray the characters' knowledge and tones, they face challenges in capturing their minds, especially for small role-playing language models (RPLMs). In this paper, we propose to enhance RPLMs via personality-indicative data. Specifically, we leverage questions from psychological scales and distill advanced RPAs to generate dialogues that grasp the minds of characters. Experimental results validate that RPLMs trained with our dataset exhibit advanced role-playing capabilities for both general and personality-related evaluations. Code and data are available at \href{https://github.com/alienet1109/RolePersonality}{this URL}.

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。

↑