OpenCharacter：使用大规模合成人设训练可定制角色扮演LLM

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas

January 26, 2025

作者: Xiaoyang Wang, Hongming Zhang, Tao Ge, Wenhao Yu, Dian Yu, Dong Yu

cs.AI

摘要

大型语言模型（LLMs）中的可定制角色扮演，也被称为角色泛化，因其在开发和部署角色扮演对话代理时的多功能性和成本效益而受到越来越多的关注。本研究探讨了一种大规模数据合成方法，以赋予LLMs角色泛化能力。我们首先使用Persona Hub中的人物角色，合成大规模角色概况，然后探索两种策略：响应重写和响应生成，以创建与角色对齐的指导性响应。为验证我们的合成指导性调整数据对角色泛化的有效性，我们使用LLaMA-3 8B模型进行监督微调（SFT）。我们表现最佳的模型加强了原始的LLaMA-3 8B Instruct模型，并在角色扮演对话中达到了与GPT-4o模型相当的性能。我们发布了我们的合成角色和指导性调整对话，以支持公共研究。

English

Customizable role-playing in large language models (LLMs), also known as character generalization, is gaining increasing attention for its versatility and cost-efficiency in developing and deploying role-playing dialogue agents. This study explores a large-scale data synthesis approach to equip LLMs with character generalization capabilities. We begin by synthesizing large-scale character profiles using personas from Persona Hub and then explore two strategies: response rewriting and response generation, to create character-aligned instructional responses. To validate the effectiveness of our synthetic instruction tuning data for character generalization, we perform supervised fine-tuning (SFT) using the LLaMA-3 8B model. Our best-performing model strengthens the original LLaMA-3 8B Instruct model and achieves performance comparable to GPT-4o models on role-playing dialogue. We release our synthetic characters and instruction-tuning dialogues to support public research.