Josip Jukić

From Robustness to Improved Generalization and Calibration in Pre-trained Language Models

2025 · Transactions of the Association for Computational Linguistics

Abstract Enforcing representation smoothness in pre-trained language models (PLMs) through Jacobian and Hessian regularization provides an effective approach for enhancing both robustness and generalization. Although such regularization methods have proven effective in computer vision, their …