Bridging Domain Expertise and Generalization for Performance Estimation 事件

Bridging Domain Expertise and Generalization for Performance Estimation arXiv:2606.06335v1 Announce Type: cross Abstract: Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data, a scenario that requires reliable indicators that can faithfully reflect model behavior without ground-truth labels. Existing approaches rely solely on the outputs of the given model whose biases are amplified once th