Spontaneous Functional Differentiation in Large Language Models: A Brain-Like Intelligence Economy
This work bridges artificial and biological intelligence by identifying universal computational principles in LLMs.
The study found that large language models spontaneously develop synergistic cores in middle layers, similar to human brains, with ablation causing catastrophic performance loss, confirming their role in abstract reasoning.
The evolution of intelligence in artificial systems provides a unique opportunity to identify universal computational principles. Here we show that large language models spontaneously develop synergistic cores where information integration exceeds individual parts remarkably similar to the human brain. Using Integrated Information Decomposition across multiple architectures we find that middle layers exhibit synergistic processing while early and late layers rely on redundancy. This organization is dynamic and emerges as a physical phase transition as task difficulty increases. Crucially ablating synergistic components causes catastrophic performance loss confirming their role as the physical entity of abstract reasoning and bridging artificial and biological intelligence.