When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
For practitioners deploying tabular models in strategic settings (e.g., credit scoring), this work provides a practical inference-time fix without retraining, though the improvement is incremental over existing methods.
This paper identifies that tabular foundation models (PFNs) fail under strategic manipulation due to prior mismatch, and proposes SPN, an inference-time method that aligns predictions with the strategic distribution, improving robustness and accuracy on real and synthetic datasets.
Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are typically designed for \emph{non-strategic} settings where data distributions are independent of deployed classifiers. In many real-world decision scenarios, however, individuals may strategically modify their features after deployment to obtain favorable outcomes, inducing a post-deployment distribution shift. This paper studies whether PFN-style tabular foundation models can generalize to such \emph{strategic} tabular data. We show that strategic manipulation creates a mismatch between the non-strategic prior learned during pretraining and the post-manipulation strategic prior, which leads to systematic prediction bias. To address this issue, we propose \textbf{Strategic Prior-data Fitted Network}~\textit{(SPN)}, an inference-time strategy-aware framework that adapts tabular foundation models to strategic environments without retraining. SPN constructs strategic in-context examples to approximate post-manipulation inputs and aligns PFN predictions with the induced strategic distribution. Experiments on real-world and synthetic tabular datasets show that SPN consistently improves robustness and predictive performance under strategic manipulation compared with both tabular foundation models and classical tabular methods.