A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles

TL;DR

This paper introduces StyleRPA, a multi-task role-playing agent that effectively imitates character linguistic styles across diverse tasks, overcoming limitations of existing RPAs that focus only on dialogue.

Contribution

The paper presents MRstyle, a new multi-task dataset, and StyleRPA, a novel agent capable of multi-domain character style imitation beyond dialogue.

Findings

StyleRPA outperforms recent open-source LLMs on 7 diverse tasks.

The MRstyle dataset includes quotations from real individuals across multiple domains.

StyleRPA demonstrates improved authenticity in character imitation across tasks.

Abstract

The advent of large language models (LLMs) has significantly propelled the advancement of Role-Playing Agents (RPAs). However, current Role-Playing Agents predominantly focus on mimicking a character's fundamental attributes while neglecting the replication of linguistic style, and they are incapable of effectively replicating characters when performing tasks beyond multi-turn dialogues, which results in generated responses that lack authenticity. The reason current RPAs lack this capability is due to the nature of existing character datasets, which lack collections of character quotations and are limited to multi-turn dialogue tasks, constraining the RPA's performance across other task domains and failing to mimic a character's linguistic style. To address this gap, we developed a multi-task role-playing dataset named MRstyle, which encompasses a substantial number of real individuals along with their quotations and covers seven different tasks. On this basis, we develop StyleRPA, a Multi-Task Role-Playing Agent (MRPA) that significantly outperforms recent open-source LLMs and RPAs baselines on 7 tasks including Dialogue, Dictionary, Composition, Story Generation, Product Description, Music Commentary, and Open Question Answering. The code and data will be released.