PsyPlay: Personality-Infused Role-Playing Conversational Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Tao, Zhu, Yuhua, Quan, Xiaojun, Liu, Cong, Wang, Qifan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916600368594944
author Yang, Tao
Zhu, Yuhua
Quan, Xiaojun
Liu, Cong
Wang, Qifan
author_facet Yang, Tao
Zhu, Yuhua
Quan, Xiaojun
Liu, Cong
Wang, Qifan
contents The current research on Role-Playing Conversational Agents (RPCAs) with Large Language Models (LLMs) primarily focuses on imitating specific speaking styles and utilizing character backgrounds, neglecting the depiction of deeper personality traits.~In this study, we introduce personality-infused role-playing for LLM agents, which encourages agents to accurately portray their designated personality traits during dialogues. We then propose PsyPlay, a dialogue generation framework that facilitates the expression of rich personalities among multiple LLM agents. Specifically, PsyPlay enables agents to assume roles with distinct personality traits and engage in discussions centered around specific topics, consistently exhibiting their designated personality traits throughout the interactions. Validation on generated dialogue data demonstrates that PsyPlay can accurately portray the intended personality traits, achieving an overall success rate of 80.31% on GPT-3.5. Notably, we observe that LLMs aligned with positive values are more successful in portraying positive personality roles compared to negative ones. Moreover, we construct a dialogue corpus for personality-infused role-playing, called PsyPlay-Bench. The corpus, which consists of 4745 instances of correctly portrayed dialogues using PsyPlay, aims to further facilitate research in personalized role-playing and dialogue personality detection.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03821
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PsyPlay: Personality-Infused Role-Playing Conversational Agents
Yang, Tao
Zhu, Yuhua
Quan, Xiaojun
Liu, Cong
Wang, Qifan
Computation and Language
The current research on Role-Playing Conversational Agents (RPCAs) with Large Language Models (LLMs) primarily focuses on imitating specific speaking styles and utilizing character backgrounds, neglecting the depiction of deeper personality traits.~In this study, we introduce personality-infused role-playing for LLM agents, which encourages agents to accurately portray their designated personality traits during dialogues. We then propose PsyPlay, a dialogue generation framework that facilitates the expression of rich personalities among multiple LLM agents. Specifically, PsyPlay enables agents to assume roles with distinct personality traits and engage in discussions centered around specific topics, consistently exhibiting their designated personality traits throughout the interactions. Validation on generated dialogue data demonstrates that PsyPlay can accurately portray the intended personality traits, achieving an overall success rate of 80.31% on GPT-3.5. Notably, we observe that LLMs aligned with positive values are more successful in portraying positive personality roles compared to negative ones. Moreover, we construct a dialogue corpus for personality-infused role-playing, called PsyPlay-Bench. The corpus, which consists of 4745 instances of correctly portrayed dialogues using PsyPlay, aims to further facilitate research in personalized role-playing and dialogue personality detection.
title PsyPlay: Personality-Infused Role-Playing Conversational Agents
topic Computation and Language
url https://arxiv.org/abs/2502.03821