Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models

Abstract

How large language models (LLMs) align with the neural representation and computation of human language is a central question in cognitive science. Using representational geometry as a mechanistic lens, we addressed this by tracking entropy, curvature, and fMRI encoding scores throughout Pythia (70M-1B) training. We identified a geometric modularization where layers self-organize into stable low- and high-complexity clusters. The low-complexity module, characterized by reduced entropy and curvature, consistently better predicted human language network activity. This alignment followed heterogeneous spatial-temporal trajectories: rapid and stable in temporal regions (AntTemp, PostTemp), but delayed and dynamic in frontal areas (IFG, IFGorb). Crucially, reduced curvature remained a robust predictor of model-brain alignment even after controlling for training progress, an effect that strengthened with model scale. These results links training-driven geometric reorganization to temporal-frontal functional specialization, suggesting that representational smoothing facilitates neural-like linguistic processing.