Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment 事件

Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment arXiv:2605.04363v2 Announce Type: replace-cross Abstract: TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift, often overfitting to the majority class in the training dataset. To address this limitation, we propose DistPFN, the first test-ti