arXiv 2510.246772025-10-28cs.CLcs.AI

通过神经元消融解析医学大语言模型中的角色认知

Dissecting Role Cognition in Medical LLMs via Neuronal Ablation

School of Information, Renmin University of China（中国人民大学信息学院）；Center of Machine Learning Research, Peking University（北京大学机器学习研究中心）；School of Artificial Intelligence, Shanghai Jiaotong University（上海交通大学人工智能学院）；Health Informatics Committee of the China Society for Scientific and Technical Information, Renmin University of China（中国科学技术信息学会健康信息技术委员会，中国人民大学）；Institute for Advanced Algorithms Research (IAAR), Shanghai, China（先进算法研究所（IAAR），上海，中国）；Memtensor Research Center, Shanghai, China（Memtensor研究中心，上海，中国）

Xun Liang, Huayi Lai, Hanyu Wang, Wentao Zhang, Linfeng Zhang, Yanfang Chen, Feiyu Xiong, Zhiyu Li

备注：: 15 pages, 9 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究提出RPNA框架，通过神经元消融和表征分析验证：当前基于提示的医学LLM角色扮演仅改变表层语言风格，未形成角色特有的推理通路，无法复现真实临床认知复杂性。

摘要：

大语言模型（LLM）已在医疗决策支持系统中获得广泛应用，尤其是在医疗问答和角色扮演模拟场景中。一种常见做法是基于提示的角色扮演（Prompt-Based Role Playing, PBRP），即指示模型采用不同临床角色（如医学生、住院医师、主治医师）来模拟各类专业行为。然而，此类角色提示对模型推理能力的影响仍不明确。本研究提出RP-Neuron-Activated Evaluation Framework（RPNA，角色神经元激活评估框架），用于评估角色提示是会在LLM中诱发独特的、角色特定的认知过程，还是仅会修改语言风格。我们在三个医疗问答数据集上测试该框架，采用神经元消融和表征分析技术评估推理通路的变化。研究结果表明，角色提示并未显著提升LLM的医疗推理能力。相反，它们主要影响表层语言特征，没有证据表明不同临床角色存在不同的推理通路或认知分化。尽管存在表层风格变化，但LLM的核心决策机制在不同角色间保持一致，这表明当前的PBRP方法无法复现现实医疗实践中存在的认知复杂性。这一发现凸显了医疗AI中角色扮演的局限性，并强调需要开发能模拟真实认知过程而非仅进行语言模仿的模型。我们已在以下代码仓库发布相关代码：https://github.com/IAAR-Shanghai/RolePlay_LLMDoctor

英文摘要：

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

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。