mean-field

The paper proposes a mean-field framework to model chain-of-thought reasoning in LLMs as a guided discovery process on a clue graph, deriving an ODE for the fraction of discovered clues and validating it experimentally.

This paper investigates how neural networks maintain high accuracy even when over 90% of input features are corrupted, deriving a centroid-based decision rule in the high-noise limit using a mean-field approach.