# Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions

arXiv: https://arxiv.org/abs/2512.12775 · HTML: https://mlsanity.com/paper/2512.12775/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 168 references that are in the map.
- First posted on arXiv 14 Dec 2025.

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

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [Long Time No See! Open-Domain Conversation with Long-Term Persona Memory](https://mlsanity.com/paper/2203.05797/) (2022)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [One Thousand and One Pairs: A "novel" challenge for long-context language models](https://mlsanity.com/paper/2406.16264/) (2024)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent](https://mlsanity.com/paper/2402.13717/) (2024)
- [You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments](https://mlsanity.com/paper/2311.09718/) (2023)
- [CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds](https://mlsanity.com/paper/2412.05631/) (2024)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [Exploring Safety-Utility Trade-Offs in Personalized Language Models](https://mlsanity.com/paper/2406.11107/) (2024)
- [Atla Selene Mini: A General Purpose Evaluation Model](https://mlsanity.com/paper/2501.17195/) (2025)
- [Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning](https://mlsanity.com/paper/2503.17662/) (2025)
- [Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarios](https://mlsanity.com/paper/2503.01532/) (2025)
- [Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs](https://mlsanity.com/paper/2502.20968/) (2025)
- [Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior](https://mlsanity.com/paper/2407.02099/) (2024)
- [Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance](https://mlsanity.com/paper/2508.19764/) (2025)
- [Label-Descriptive Patterns and Their Application to Characterizing Classification Errors](https://mlsanity.com/paper/2110.09599/) (2021)
- [CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents](https://mlsanity.com/paper/2405.19778/) (2024)

## Built on by (most cited first, 12 of 12)

- [Beyond Static Personas: Situational Personality Steering for Large Language Models](https://mlsanity.com/paper/2604.13846/) (2026)
- [The Autocorrelation Blind Spot: Why 42% of Turn-Level Findings in LLM Conversation Analysis May Be Spurious](https://mlsanity.com/paper/2604.14414/) (2026)
- [ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?](https://mlsanity.com/paper/2606.05553/) (2026)
- [PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue](https://mlsanity.com/paper/2608.06975/) (2026)
- [Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication](https://mlsanity.com/paper/2606.12433/) (2026)
- [Sycophancy as Material Failure under Pushback Loading: A Multi-Axis Characterization Across Three Loading Cases and up to Seventeen Material Charges](https://mlsanity.com/paper/2606.16617/) (2026)
- [AI YOU Town: Make Friends and Money with Your Digital Twin](https://mlsanity.com/paper/2607.10539/) (2026)
- [Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue](https://mlsanity.com/paper/2607.11437/) (2026)
- [Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models](https://mlsanity.com/paper/2609.08637/) (2026)
- [Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents](https://mlsanity.com/paper/2609.13637/) (2026)
- [RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue](https://mlsanity.com/paper/2609.16614/) (2026)
- [One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction](https://mlsanity.com/paper/2609.21626/) (2026)

## Abstract (arXiv)

Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation. Yet, they are typically evaluated only in short, single-round settings that do not reflect real-world usage. We introduce an evaluation protocol that combines long persona dialogues (over 100 rounds) and evaluation datasets to create dialogue-conditioned benchmarks that can robustly measure long-context effects. We then investigate the effects of dialogue length on persona fidelity, instruction-following, and safety of seven state-of-the-art open- and closed-weight LLMs. We find that persona fidelity degrades over the course of dialogues, especially in goal-oriented conversations, where models must sustain both persona fidelity and instruction following. We identify a trade-off between fidelity and instruction following, with non-persona baselines initially outperforming persona-assigned models; as dialogues progress and fidelity fades, persona responses become increasingly similar to baseline responses. Our findings highlight the fragility of persona applications in extended interactions and our work provides a protocol to systematically measure such failures.