多语言语言模型中的计算病变分离共享和语言特定的脑对齐
Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
AI总结：
研究通过多语言大语言模型创建计算病变，揭示语言处理的共享与特定机制，发现共享核心减少整体脑编码相关性，而语言特定病变保持跨语言分离但削弱匹配母语的脑预测性。
摘要：
大脑如何支持不同语言中的语言是一个基础的神经科学问题，也是多语言人工智能的有用测试。神经影像学已识别出跨语言的语言响应脑区，但无法单独显示其处理是共享还是语言特定的。本文利用六个多语言大语言模型作为可控系统，通过零化重要跨语言或特定语言的小参数集创建目标性“计算病变”。然后比较完整和病变模型在预测功能性磁共振成像（fMRI）响应方面的表现，该响应基于100分钟的自然故事聆听，涉及英语、中文和法语的母语者（112人）。零化紧凑的共享核心使整体脑编码相关性减少60.32%，而语言特定病变保持嵌入空间的跨语言分离，但选择性削弱匹配母语的脑预测性。这些结果支持共享骨干与嵌入式专门化相结合的结构，并提供研究多语言脑模型对齐的因果框架。
英文摘要：
How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identified language-responsive brain regions across languages, but it cannot by itself show whether the underlying processing is shared or language-specific. Here we use six multilingual large language models (LLMs) as controllable systems and create targeted ``computational lesions'' by zeroing small parameter sets that are important across languages or especially important for one language. We then compare intact and lesioned models in predicting functional magnetic resonance imaging (fMRI) responses during 100 minutes of naturalistic story listening in native English, Chinese and French (112 participants). Lesioning a compact shared core reduces whole-brain encoding correlation by 60.32% relative to intact models, whereas language-specific lesions preserve cross-language separation in embedding space but selectively weaken brain predictivity for the matched native language. These results support a shared backbone with embedded specializations and provide a causal framework for studying multilingual brain-model alignment.
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。
