大型語言模型中湧現的模組化認知架構

摘要

人腦展現出高度的功能特化，不同的神經網絡分別支持語言、形式推理、對他人心智的推理，以及對物理世界的推理。這種模組化組織究竟是智慧系統建構的基本原則，抑或是生物大腦在演化過程中的偶然產物？在此，我們檢驗此種相似的組織是否出現於大型語言模型中——這是另一類透過截然不同的優化過程所創造的智慧系統。透過跨四個認知領域（語言、形式推理、社會推理、物理推理）共 N=46 個任務的電路分析，我們發現大型語言模型發展出與人腦相互映照的模組化架構：在人腦中啟用相同網絡的任務，會在大語言模型中招募重疊的神經元；而啟用不同網絡的任務，則會招募不同的神經元。模組化在大腦與神經網絡中趨同出現，此一事實顯示模組化可能為智慧系統的基本屬性。

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.