# Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

arXiv: https://arxiv.org/abs/2401.12474 · HTML: https://mlsanity.com/paper/2401.12474/

## Key facts

- Cited by 104 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## Builds on (most cited first, 11 of 11)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [The False Promise of Imitating Proprietary LLMs](https://mlsanity.com/paper/2305.15717/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Wider and Deeper LLM Networks are Fairer LLM Evaluators](https://mlsanity.com/paper/2308.01862/) (2023)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [Coarse-to-Fine Pre-training for Named Entity Recognition](https://mlsanity.com/paper/2010.08210/) (2020)

## Built on by (most cited first, 30 of 104)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [A Survey on Self-Evolution of Large Language Models](https://mlsanity.com/paper/2404.14387/) (2024)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [From Role-Play to Drama-Interaction: An LLM Solution](https://mlsanity.com/paper/2405.14231/) (2024)
- [SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning](https://mlsanity.com/paper/2504.19162/) (2025)
- [Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles](https://mlsanity.com/paper/2502.18968/) (2025)
- [IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation](https://mlsanity.com/paper/2407.01093/) (2024)
- [AI Safety in Generative AI Large Language Models: A Survey](https://mlsanity.com/paper/2407.18369/) (2024)
- [SDPO: Segment-Level Direct Preference Optimization for Social Agents](https://mlsanity.com/paper/2501.01821/) (2025)
- [Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning](https://mlsanity.com/paper/2503.17662/) (2025)
- [Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval](https://mlsanity.com/paper/2410.23041/) (2024)
- [CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation](https://mlsanity.com/paper/2502.09082/) (2025)
- [OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas](https://mlsanity.com/paper/2501.15427/) (2025)
- [SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent](https://mlsanity.com/paper/2412.08389/) (2024)
- [TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models](https://mlsanity.com/paper/2405.18027/) (2024)
- [Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs](https://mlsanity.com/paper/2502.20968/) (2025)
- [RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems](https://mlsanity.com/paper/2409.16727/) (2024)
- [AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation](https://mlsanity.com/paper/2506.00551/) (2025)
- [Population-Aligned Persona Generation for LLM-based Social Simulation](https://mlsanity.com/paper/2509.10127/) (2025)
- [Mitigating Hallucination in Fictional Character Role-Play](https://mlsanity.com/paper/2406.17260/) (2024)
- [A Survey on LLM-based Conversational User Simulation](https://mlsanity.com/paper/2604.24977/) (2026)
- [Self-Cognition in Large Language Models: An Exploratory Study](https://mlsanity.com/paper/2407.01505/) (2024)
- [Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models](https://mlsanity.com/paper/2411.00492/) (2024)
- [BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model](https://mlsanity.com/paper/2408.10903/) (2024)
- [NarraBench: A Comprehensive Framework for Narrative Benchmarking](https://mlsanity.com/paper/2510.09869/) (2025)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends](https://mlsanity.com/paper/2409.14195/) (2024)

## Abstract (arXiv)

Considerable efforts have been invested in augmenting the role-playing proficiency of open-source large language models (LLMs) by emulating proprietary counterparts. Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora. Thus, in this study, we introduce Ditto, a self-alignment method for role-play. Ditto capitalizes on character knowledge, encouraging an instruction-following LLM to simulate role-play dialogues as a variant of reading comprehension. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold regarding the number of roles. Subsequently, we fine-tune the LLM using this self-generated dataset to augment its role-playing capabilities. Upon evaluating our meticulously constructed and reproducible role-play benchmark and the roleplay subset of MT-Bench, Ditto, in various parameter scales, consistently maintains a consistent role identity and provides accurate role-specific knowledge in multi-turn role-play conversations. Notably, it outperforms all open-source role-play baselines, showcasing performance levels comparable to advanced proprietary chatbots. Furthermore, we present the first comprehensive cross-supervision alignment experiment in the role-play domain, revealing that the intrinsic capabilities of LLMs confine the knowledge within role-play. Meanwhile, the role-play styles can be easily acquired with the guidance of smaller models. We open-source related resources at https://github.com/OFA-Sys/Ditto.