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

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

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas: 6 upvotes on Hugging Face Daily Papers, #12 of 14 papers on 2025-01-28. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.