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

TL;DR

This paper introduces a method to improve role-playing language models by incorporating personality-indicative data, enabling them to better capture characters' minds and personalities in dialogues.

Contribution

It proposes leveraging psychological scale questions and distillation techniques to enhance small RPLMs' ability to portray character minds and personalities.

Findings

Enhanced role-playing capabilities demonstrated in experiments

Models better capture character personalities and minds

Code and data publicly available

Abstract

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}.