模块化认知架构在大语言模型中的涌现

摘要

人脑展现出显著的功能特化程度，不同的网络分别支持语言、形式推理、关于他人心智的推理以及关于物理世界的推理。这种模块化组织是智能系统构建的基本原理，还是生物大脑特有的进化偶然事件？在此，我们检验了类似的组织是否出现在大语言模型中——另一类通过截然不同的优化过程产生的智能系统。通过对跨越四个认知领域（语言、形式推理、社会推理、物理推理）的N=46个任务进行电路分析，我们发现大语言模型发展出了与人脑镜像对应的模块化架构：在人脑中调用相同网络的任务在大语言模型中会招募重叠的神经元，而调用不同网络的任务则会招募不同的神经元。模块化在脑与神经网络中的趋同涌现表明，它可能是智能系统的一项基本属性。

English

The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models--another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains and neural networks suggests that it may be a fundamental property of intelligent systems.