Results from experiments on three large real-world benchmark datasets demonstrate that OptFeature performs well in terms of accuracy and efficiency. Additional studies support the feasibility of our method.

Even a well-calibrated LLM may struggle to estimate uncertainty during fine-tuning duetocatastrophic forgetting ofgeneral knowledge [84].

Therefore, it's important to study whether we can and also how to

We study the implicit bias of optimization in robust empirical risk minimization (robust ERM) and its connection with robust generalization.