mlsanityData to 7 Oct 2026

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

arXiv 2501.15427 ↗First posted 26 Jan 2025cs.CLcited by 25

Not on the map. Why?

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.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 26 Jan 2025.

Builds on

33 of 38 references.

References · 33

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2024GPT-4o System Cardcited by 4,467
  9. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  12. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
21 more
  1. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  2. 2023LIMA: Less Is More for Alignmentcited by 1,080
  3. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  4. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  5. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  6. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  7. 2023RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Modelscited by 173
  8. 2023MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuningcited by 149
  9. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluationcited by 139
  10. 2024InFoBench: Evaluating Instruction Following Ability in Large Language Modelscited by 128
  11. 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?cited by 119
  12. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignmentcited by 104
  13. 2024Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Modelscited by 99
  14. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 89
  15. 2023CharacterChat: Learning towards Conversational AI with Personalized Social Supportcited by 58
  16. 2024Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoningcited by 58
  17. 2023ChatHaruhi: Reviving Anime Character in Reality via Large Language Modelcited by 57
  18. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agentscited by 48
  19. 2021NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversationcited by 35
  20. 2023CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Modelscited by 34
  21. 2024StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 15.

25 papers.

Sort:

By area:

  1. 2025DeepPersona: A Generative Engine for Scaling Deep Synthetic Personascited by 14
  2. 2026HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playingcited by 10
  3. 2025Towards Interactive Intelligence for Digital Humanscited by 8
  4. 2025Evaluating, Synthesizing, and Enhancing for Customer Support Conversationcited by 7
  5. 2025MOA: Multi-Objective Alignment for Role-Playing Agentscited by 5
  6. 2025Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactionscited by 4
  7. 2025Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agentscited by 3
  8. 2025FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipelinecited by 3
  9. 2026PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistencycited by 3
  10. 2026PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Modelscited by 3
  11. 2026Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axescited by 2
  12. 2026Beyond Static Personas: Situational Personality Steering for Large Language Modelscited by 2
13 more
  1. 2026When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skillscited by 2
  2. 2025Understanding Generalization in Role-Playing Models via Information Theorycited by 1
  3. 2026Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agentscited by 1
  4. 2026Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inferencecited by 1
  5. 2025Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrievalcited by 0
  6. 2025Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novelscited by 0
  7. 2026Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulationcited by 0
  8. 2026Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playingcited by 0
  9. 2026BOOKMARKS: Efficient Active Storyline Memory for Role-playingcited by 0
  10. 2026Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluationcited by 0
  11. 2026The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMscited by 0
  12. 2026TalkMatrix: Generating Character Dialogue that is Both Consistent and Diversecited by 0
  13. 2026Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populationscited by 0