大语言模型中的类脑功能组织
Brain-like Functional Organization within Large Language Models
AI总结：
本研究首次将大语言模型的人工神经元亚群与人脑功能脑网络关联，发现BERT、Llama 1-3等模型存在类脑功能组织，且随模型能力提升该组织会优化计算多样性与功能特化的平衡，为类脑AGI开发提供新视角。
摘要：
长期以来，人脑一直启发着人工智能（AI）的研究。近期，神经影像学研究提供了令人信服的证据，表明人工神经网络（ANNs）的计算表征与人脑对刺激的神经响应之间存在一致性，这说明ANNs可能采用了类脑的信息处理策略。尽管这种一致性已在视觉、听觉和语言等多种感觉模态中被观察到，但研究大多聚焦于群体层面的人工神经元（ANs）行为，而对支撑这类类脑处理过程的单个AN功能组织仍 largely 未被探索。本研究通过将人工神经元亚群直接与功能脑网络（FBNs，人脑的基础组织结构）相关联，填补了这一空白。具体而言，我们从大语言模型（LLMs）中ANs的时间响应中提取代表性模式，并将其作为固定回归量构建体素级编码模型，以预测功能磁共振成像（fMRI）记录的大脑活动。该框架将AN亚群与FBNs关联起来，能够描绘LLMs内部的类脑功能组织。我们的研究结果表明，LLMs（BERT和Llama 1-3）展现出类脑功能架构，其人工神经元亚群映射了已被充分证实的FBNs的组织模式。值得注意的是，LLMs的类脑功能组织会随着模型复杂度和能力的提升而演化，在计算行为的多样性与功能特化的一致性之间实现了更好的平衡。本研究首次探索了LLMs内部的类脑功能组织，为基于人脑原理开发通用人工智能（AGI）提供了新的见解。
英文摘要：
The human brain has long inspired the pursuit of artificial intelligence (AI). Recently, neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli, suggesting that ANNs may employ brain-like information processing strategies. While such alignment has been observed across sensory modalities--visual, auditory, and linguistic--much of the focus has been on the behaviors of artificial neurons (ANs) at the population level, leaving the functional organization of individual ANs that facilitates such brain-like processes largely unexplored. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs), the foundational organizational structure of the human brain. Specifically, we extract representative patterns from temporal responses of ANs in large language models (LLMs), and use them as fixed regressors to construct voxel-wise encoding models to predict brain activity recorded by functional magnetic resonance imaging (fMRI). This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within LLMs. Our findings reveal that LLMs (BERT and Llama 1-3) exhibit brain-like functional architecture, with sub-groups of artificial neurons mirroring the organizational patterns of well-established FBNs. Notably, the brain-like functional organization of LLMs evolves with the increased sophistication and capability, achieving an improved balance between the diversity of computational behaviors and the consistency of functional specializations. This research represents the first exploration of brain-like functional organization within LLMs, offering novel insights to inform the development of artificial general intelligence (AGI) with human brain principles.
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。
