# The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models

arXiv: https://arxiv.org/abs/2601.05376 · HTML: https://mlsanity.com/paper/2601.05376/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [Medical Large Language Model Benchmarks Should Prioritize Construct Validity](https://mlsanity.com/paper/2503.10694/) (2025)
- [Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts](https://mlsanity.com/paper/2505.17127/) (2025)
- [PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions](https://mlsanity.com/paper/2505.17818/) (2025)
- [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025)
- [Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks](https://mlsanity.com/paper/2408.08631/) (2024)
- [Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond](https://mlsanity.com/paper/2502.03945/) (2025)
- [PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming](https://mlsanity.com/paper/2509.03728/) (2025)

## Built on by (most cited first, 3 of 3)

- [SLMJury: Can Small Language Models Judge as Well as Large Ones?](https://mlsanity.com/paper/2606.07810/) (2026)
- [Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs](https://mlsanity.com/paper/2604.11120/) (2026)
- [Defeat Devices in AI Systems](https://mlsanity.com/paper/2606.28863/) (2026)

## Abstract (arXiv)

Persona conditioning can be viewed as a behavioral prior for large language models (LLMs) and is often assumed to confer expertise and improve safety in a monotonic manner. However, its effects on high-stakes clinical decision-making remain poorly characterized. We systematically evaluate persona-based control in clinical LLMs, examining how professional roles (e.g., Emergency Department physician, nurse) and interaction styles (bold vs. cautious) influence behavior across models and medical tasks. We assess performance on clinical triage and patient-safety tasks using multidimensional evaluations that capture task accuracy, calibration, and safety-relevant risk behavior. We find systematic, context-dependent, and non-monotonic effects: Medical personas improve performance in critical care tasks, yielding gains of up to ~+20% in accuracy and calibration, but degrade performance in primary-care settings by comparable margins. Interaction style modulates risk propensity and sensitivity, but it's highly model-dependent. While aggregated LLM-judge rankings favor medical over non-medical personas in safety-critical cases, we found that human clinicians show moderate agreement on safety compliance (average Cohen's kappa = 0.43) but indicate a low confidence in 95.9% of their responses on reasoning quality. Our work shows that personas function as behavioral priors that introduce context-dependent trade-offs rather than guarantees of safety or expertise. The code is available at https://github.com/rsinghlab/PersonaParadox.