受损多模态语言模型再现失语症患者的图片命名模式
Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns
浏览论文内容
中文总结 AI 辅助
研究未针对临床模拟设计的通用语言模型能否再现失语症患者图片命名错误模式，通过对多模态语言模型进行扰动配置，建立定量框架再现个体失语症错误模式，表明语言模型或可成为中风后失语症患者数字替身。
中文摘要 AI 辅助
中风后的失语症通常会产生具有特征性的系统性命名错误，但尚未测试未针对临床模拟设计的通用语言模型是否能再现这些模式。我们研究了：对多模态语言模型进行损伤或可控扰动是否能再现图片命名中的不同类型错误；该框架能否再现个体失语症患者的完整错误特征。使用LLaVA 1.6，评估了改变应用于模型单元的噪声层、比例和数量的扰动配置。在费城命名测试中检查了278名失语症患者，用经过验证的神经分类器将反应分为七类。七个反应类别中的六个在不同参数空间区域以临床可比的比例出现，形式性错语除外。搜索扰动空间发现，97.8%的失语症患者在七个类别中的至少六个类别中再现了个体错误特征，79.5%的患者在所有七个类别中都再现了。蒙特卡罗基线证实这种匹配反映了类别间的联合结构而非边缘重叠。这些结果建立了一个在图片命名中再现个体失语症错误模式的定量框架，表明语言模型有可能成为中风后失语症患者的数字替身。
英文摘要
Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for clinical simulation can reproduce these patterns remains untested. We investigated (1) whether lesions or controlled perturbations to a multimodal language model can reproduce different types of errors in picture naming, and (2) whether the framework can reproduce the complete error profile of individual persons with aphasia (PWAs). Using LLaVA 1.6, we evaluated perturbation configurations that varied the layer, proportion, and amount of noise applied to model units. We examined 278 PWAs on the Philadelphia Naming Test, classifying responses into seven categories using a validated neural classifier. Six of seven response categories (correct, semantic, mixed, unrelated, neologism, no response errors) emerged at clinically-comparable proportions across distinct parameter space regions, with formal paraphasia being the exception. Searching the perturbation space revealed configurations that reproduced the individual error profile in at least six of seven categories for 97.8% of PWAs and in all seven categories for 79.5% of PWAs. Monte Carlo baselines confirmed that this matching reflects joint inter-category structure rather than marginal overlap. These results establish a quantitative framework for reproducing individual aphasic error patterns in picture naming. They suggest the potential for language models to serve as digital twins of individuals with post-stroke aphasia.
发表机构
- University of South Carolina（南卡罗来纳大学）
- ALLT.AI, LLC（ALLT.AI有限责任公司）
机构由 AI 辅助整理，请以论文原文为准。
