Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors

ArXi:2603.18593v1 Announce Type: new We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing their conditional distributions. In this space, distances between models approximate the KL divergence between the corresponding conditional distributions. Experiments on a large collection of publicly available language models show that the maps capture meaningful global structure, including relationships to model attributes and task performance.