# Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing

arXiv: https://arxiv.org/abs/2405.07726 · HTML: https://mlsanity.com/paper/2405.07726/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 13 May 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [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)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://mlsanity.com/paper/2310.00746/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent](https://mlsanity.com/paper/2402.13717/) (2024)
- [From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2401.02777/) (2024)
- [MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education](https://mlsanity.com/paper/2404.06711/) (2024)
- [Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances](https://mlsanity.com/paper/2204.10825/) (2022)
- [LARP: Language-Agent Role Play for Open-World Games](https://mlsanity.com/paper/2312.17653/) (2023)
- [RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2312.16132/) (2023)
- [RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models](https://mlsanity.com/paper/2401.09432/) (2023)
- [Unveiling the Secrets of Engaging Conversations: Factors that Keep Users Hooked on Role-Playing Dialog Agents](https://mlsanity.com/paper/2402.11522/) (2024)
- [Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement](https://mlsanity.com/paper/2402.10618/) (2024)
- [Apollonion: Profile-centric Dialog Agent](https://mlsanity.com/paper/2404.08692/) (2024)

## Built on by (most cited first, 17 of 17)

- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction](https://mlsanity.com/paper/2505.20277/) (2025)
- [Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency](https://mlsanity.com/paper/2512.00461/) (2025)
- [AI-native Memory: A Pathway from LLMs Towards AGI](https://mlsanity.com/paper/2406.18312/) (2024)
- [Towards Interactive Intelligence for Digital Humans](https://mlsanity.com/paper/2512.13674/) (2025)
- [Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation](https://mlsanity.com/paper/2509.06337/) (2025)
- [Codifying Character Logic in Role-Playing](https://mlsanity.com/paper/2505.07705/) (2025)
- [Deriving Character Logic from Storyline as Codified Decision Trees](https://mlsanity.com/paper/2601.10080/) (2026)
- [PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models](https://mlsanity.com/paper/2605.17044/) (2026)
- [Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation](https://mlsanity.com/paper/2510.16829/) (2025)
- [Multi-Stage Patient Role-Playing Framework for Realistic Clinical Interactions](https://mlsanity.com/paper/2601.10951/) (2026)
- [StudentSim: Training LLM-based Student Simulators](https://mlsanity.com/paper/2609.01591/) (2026)
- [Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels](https://mlsanity.com/paper/2512.07474/) (2025)
- [Codified Foreshadowing-Payoff Text Generation](https://mlsanity.com/paper/2601.07033/) (2026)
- [Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents](https://mlsanity.com/paper/2609.13637/) (2026)
- [Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents](https://mlsanity.com/paper/2609.28609/) (2026)
- [Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation](https://mlsanity.com/paper/2610.10988/) (2026)

## Abstract (arXiv)

Persona-driven role-playing (PRP) aims to build AI characters that can respond to user queries by faithfully sticking with all persona statements. Unfortunately, existing faithfulness criteria for PRP are limited to coarse-grained LLM-based scoring without a clear definition or formulation. This paper presents a pioneering exploration to quantify PRP faithfulness as a fine-grained and explainable criterion, which also serves as a reliable reference for optimization. Our criterion first discriminates persona statements into active and passive constraints by identifying the query-statement relevance. Then, we incorporate all constraints following the principle that the AI character's response should be (a) entailed by active (relevant) constraints and (b) not contradicted by passive (irrelevant) constraints. We translate this principle mathematically into a novel Active-Passive-Constraint (APC) score, a constraint-wise sum of natural language inference (NLI) scores weighted by relevance scores. In practice, we build the APC scoring system by symbolically distilling small discriminators from GPT-4 for efficiency. We validate the quality of the APC score against human evaluation based on example personas with tens of statements, and the results show a high correlation. We further leverage it as a reward system in direct preference optimization (DPO) for better AI characters. Our experiments offer a fine-grained and explainable comparison between existing PRP techniques, revealing their advantages and limitations. We further find APC-based DPO to be one of the most competitive techniques for sticking with all constraints and can be well incorporated with other techniques. We then extend the scale of the experiments to real persons with hundreds of statements and reach a consistent conclusion.