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

arXiv: https://arxiv.org/abs/2501.15427 · HTML: https://mlsanity.com/paper/2501.15427/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 38 references that are in the map.
- First posted on arXiv 26 Jan 2025.

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://mlsanity.com/paper/2310.00746/) (2023)
- [MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning](https://mlsanity.com/paper/2311.10774/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models](https://mlsanity.com/paper/2402.13064/) (2024)
- [PersonaGym: Evaluating Persona Agents and LLMs](https://mlsanity.com/paper/2407.18416/) (2024)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [ChatHaruhi: Reviving Anime Character in Reality via Large Language Model](https://mlsanity.com/paper/2308.09597/) (2023)
- [Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning](https://mlsanity.com/paper/2403.02333/) (2024)
- [SocialBench: Sociality Evaluation of Role-Playing Conversational Agents](https://mlsanity.com/paper/2403.13679/) (2024)

## Built on by (most cited first, 25 of 25)

- [DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas](https://mlsanity.com/paper/2511.07338/) (2025)
- [Towards Interactive Intelligence for Digital Humans](https://mlsanity.com/paper/2512.13674/) (2025)
- [HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing](https://mlsanity.com/paper/2601.21459/) (2026)
- [Evaluating, Synthesizing, and Enhancing for Customer Support Conversation](https://mlsanity.com/paper/2508.04423/) (2025)
- [MOA: Multi-Objective Alignment for Role-Playing Agents](https://mlsanity.com/paper/2512.09756/) (2025)
- [Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions](https://mlsanity.com/paper/2502.13135/) (2025)
- [Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents](https://mlsanity.com/paper/2509.15233/) (2025)
- [FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline](https://mlsanity.com/paper/2510.06800/) (2025)
- [PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency](https://mlsanity.com/paper/2603.25620/) (2026)
- [PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models](https://mlsanity.com/paper/2605.17044/) (2026)
- [When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills](https://mlsanity.com/paper/2608.03700/) (2026)
- [Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes](https://mlsanity.com/paper/2601.04716/) (2026)
- [Beyond Static Personas: Situational Personality Steering for Large Language Models](https://mlsanity.com/paper/2604.13846/) (2026)
- [Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents](https://mlsanity.com/paper/2606.25632/) (2026)
- [Understanding Generalization in Role-Playing Models via Information Theory](https://mlsanity.com/paper/2512.17270/) (2025)
- [Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference](https://mlsanity.com/paper/2608.26674/) (2026)
- [Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval](https://mlsanity.com/paper/2510.12014/) (2025)
- [Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels](https://mlsanity.com/paper/2512.07474/) (2025)
- [Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation](https://mlsanity.com/paper/2602.15832/) (2026)
- [Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing](https://mlsanity.com/paper/2605.04733/) (2026)
- [BOOKMARKS: Efficient Active Storyline Memory for Role-playing](https://mlsanity.com/paper/2605.14169/) (2026)
- [Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation](https://mlsanity.com/paper/2607.27816/) (2026)
- [The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs](https://mlsanity.com/paper/2609.07117/) (2026)
- [TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse](https://mlsanity.com/paper/2609.19022/) (2026)
- [Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations](https://mlsanity.com/paper/2609.29928/) (2026)

## Abstract (arXiv)

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.