Dissecting Role Cognition in Medical LLMs via Neuronal Ablation

TL;DR

This paper investigates whether role prompts in medical LLMs induce genuine role-specific reasoning or merely superficial linguistic changes, finding that current methods do not replicate real-world cognitive diversity.

Contribution

Introduces the RPNA framework to evaluate role-induced cognitive differences in medical LLMs, revealing that role prompts mainly alter style without affecting reasoning pathways.

Findings

Role prompts do not significantly improve reasoning abilities.

Surface-level linguistic features are primarily affected by role prompts.

Core decision mechanisms remain uniform across roles.

Abstract

Large language models (LLMs) have gained significant traction in medical decision support systems, particularly in the context of medical question answering and role-playing simulations. A common practice, Prompt-Based Role Playing (PBRP), instructs models to adopt different clinical roles (e.g., medical students, residents, attending physicians) to simulate varied professional behaviors. However, the impact of such role prompts on model reasoning capabilities remains unclear. This study introduces the RP-Neuron-Activated Evaluation Framework(RPNA) to evaluate whether role prompts induce distinct, role-specific cognitive processes in LLMs or merely modify linguistic style. We test this framework on three medical QA datasets, employing neuron ablation and representation analysis techniques to assess changes in reasoning pathways. Our results demonstrate that role prompts do not significantly enhance the medical reasoning abilities of LLMs. Instead, they primarily affect surface-level linguistic features, with no evidence of distinct reasoning pathways or cognitive differentiation across clinical roles. Despite superficial stylistic changes, the core decision-making mechanisms of LLMs remain uniform across roles, indicating that current PBRP methods fail to replicate the cognitive complexity found in real-world medical practice. This highlights the limitations of role-playing in medical AI and emphasizes the need for models that simulate genuine cognitive processes rather than linguistic imitation.We have released the related code in the following repository:https: //github.com/IAAR-Shanghai/RolePlay_LLMDoctor