Controllable Prompt Tuning For Balancing Group Distributional Robustness

arXiv:2403.02695v1 Announce Type: new
Abstract: Models trained on data composed of different groups or domains can suffer from severe performance degradation under distribution shifts. While recent methods have largely focused on optimizing the worst-group objective, this often comes at the expense of good performance on other groups. To address this problem, we introduce an optimization scheme to achieve good performance across groups and find a good solution for all without severely sacrificing performance on any of them. However, directly applying …

abstract arxiv cs.lg data distribution domains good performance prompt prompt tuning robustness type