Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary

ArXi:2510.03271v2 Announce Type: replace-cross Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in revealing core model properties and interpreting behaviors. While analyzing the decision boundary of large language models (LLMs) has attracted increasing attention recently, constructing it for mainstream LLMs remains computationally infeasible due to the enormous sequence-level output spaces and the autoregressive nature of LLMs.