[论文] Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment i...

论文概要

研究领域: NLP
作者: Mariano Barone, Francesco Di Serio, Roberto Moio
发布时间: 2026-04-22
arXiv: 2604.20791

中文摘要

大型语言模型（LLMs）越来越多地部署在医疗保健领域，但它们在沟通方面与临床标准的对齐程度仍然量化不足。我们对通用和专业领域LLM在结构化医学解释和真实医患互动中进行了多维度评估，分析语义保真度、可读性和情感共鸣。基线模型放大了情感极性相对于医生（非常负面：43.14-45.10% vs. 37.25%），在GPT-5和Claude等较大架构中产生了显著更高的语言复杂度（FKGL高达16.91-17.60 vs. 医生撰写回复的11.47-12.50）。以共情为导向的提示减少了极端负面性并降低了年级水平复杂度（GPT-5最多降低-6.87 FKGL点），但并未显著增加语义保真度。协作重写产生最强的整体对齐。改写配置实现了与医生答案最高的语义相似性（平均高达0.93），同时持续改善可读性并降低情感极端性。双重利益相关者评估显示，没有模型在认知标准上超越医生，而患者始终偏好改写变体以获取清晰度和情感基调。这些发现表明，LLMs作为协作沟通增强器而非临床专业知识的替代品时功能最有效。

原文摘要

Large Language Models (LLMs) are increasingly deployed in healthcare, yet their communicative alignment with clinical standards remains insufficiently quantified. We conduct a multidimensional evaluation of general-purpose and domain-specialized LLMs across structured medical explanations and real-world physician-patient interactions, analyzing semantic fidelity, readability, and affective resonance. Baseline models amplify affective polarity relative to physicians (Very Negative: 43.14-45.10% vs. 37.25%) and, in larger architectures such as GPT-5 and Claude, produce substantially higher linguistic complexity (FKGL up to 16.91-17.60 vs. 11.47-12.50 in physician-authored responses). Empathy-oriented prompting reduces extreme negativity and lowers grade-level complexity (up to -6.87 FKGL poi...

自动采集于 2026-04-24

#论文 #arXiv #NLP #小凯