# Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning

arXiv: https://arxiv.org/abs/2503.17662 · HTML: https://mlsanity.com/paper/2503.17662/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 64 references that are in the map.
- First posted on arXiv 22 Mar 2025.

## Builds on (most cited first, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [A Persona-Based Neural Conversation Model](https://mlsanity.com/paper/1603.06155/) (2016)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [Human Alignment of Large Language Models through Online Preference Optimisation](https://mlsanity.com/paper/2403.08635/) (2024)
- [A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data](https://mlsanity.com/paper/1911.04700/) (2019)
- [Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs](https://mlsanity.com/paper/2305.11792/) (2023)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [DynaEval: Unifying Turn and Dialogue Level Evaluation](https://mlsanity.com/paper/2106.01112/) (2021)

## Built on by (most cited first, 27 of 27)

- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [A Survey on LLM-based Conversational User Simulation](https://mlsanity.com/paper/2604.24977/) (2026)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards](https://mlsanity.com/paper/2507.17147/) (2025)
- [Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs](https://mlsanity.com/paper/2603.19313/) (2026)
- [Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations](https://mlsanity.com/paper/2508.02016/) (2025)
- [Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need](https://mlsanity.com/paper/2510.11734/) (2025)
- [The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems](https://mlsanity.com/paper/2510.24831/) (2025)
- [Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines](https://mlsanity.com/paper/2512.11844/) (2025)
- [Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation](https://mlsanity.com/paper/2510.16829/) (2025)
- [Multilingual Agent-Based World Modeling for Social Science](https://mlsanity.com/paper/2512.07195/) (2025)
- [Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents](https://mlsanity.com/paper/2603.01438/) (2026)
- [Context-Value-Action Architecture for Value-Driven Large Language Model Agents](https://mlsanity.com/paper/2604.05939/) (2026)
- [Layered Mutability: Continuity and Governance in Persistent Self-Modifying Agents](https://mlsanity.com/paper/2604.14717/) (2026)
- [When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis](https://mlsanity.com/paper/2604.27228/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack](https://mlsanity.com/paper/2506.14539/) (2025)
- [Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications](https://mlsanity.com/paper/2511.02979/) (2025)
- [Partial Policy Gradients for RL in LLMs](https://mlsanity.com/paper/2603.06138/) (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)
- [Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness](https://mlsanity.com/paper/2606.10413/) (2026)
- [Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs](https://mlsanity.com/paper/2607.23545/) (2026)
- [EmoPatient: An Emotion-Directed Patient Simulator for Realistic Palliative Care Communication Training](https://mlsanity.com/paper/2608.07495/) (2026)
- [Investigating Assistant Bias in LLM User Simulators Using a Role Vector](https://mlsanity.com/paper/2609.00608/) (2026)
- [Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents](https://mlsanity.com/paper/2609.28609/) (2026)
- [OSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue](https://mlsanity.com/paper/2609.34418/) (2026)

## Abstract (arXiv)

In recent years, large language models (LLMs) have achieved breakthrough progress in many dialogue generation tasks. However, their lack of emotion and fine-grained role awareness limits the model's ability to provide personalized and diverse interactions further. Current methods face high costs in collecting high-quality annotated data for scenarios such as role-playing, and traditional human alignment methods are difficult to deploy due to the inherent diversity of model behavior in role-playing scenarios. Inspired by the alignment of models for safety behaviors through RLHF (Reinforcement Learning from Human Feedback), in this paper, we revisit model role-playing behavior from the perspective of persona alignment and propose a novel annotation-free framework named textbfunderlinePersona-Aware textbfunderlineContrastive textbfunderlineLearning (PCL) to align LLMs' behavior during role-playing, enhancing the model's role consistency. Specifically, we first design a role chain method to encourage the model to self-question based on the role characteristics and dialogue context to adjust personality consistency. Then, we further enhance the model's role-playing strategy through iterative contrastive learning between the use of role characteristics and not. Experiments on both black-box and white-box LLMs show that LLMs equipped with PCL significantly outperform vanilla LLMs under automatic evaluation methods (CharEval & GPT-4) and human expert evaluation.