Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

ArXi:2602.08920v2 Announce Type: replace Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping.