Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data
This work addresses the challenge of making role-playing agents more psychologically accurate for applications in entertainment, education, or human-computer interaction, but it is incremental as it builds on existing methods with a new dataset.
The paper tackles the problem of role-playing language models (RPLMs) struggling to capture characters' minds, especially in smaller models, by enhancing them with personality-indicative data generated from psychological scales and advanced RPAs. The result shows that RPLMs trained with this dataset exhibit improved role-playing capabilities in general and personality-related evaluations, with experimental validation.
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}.