When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach

TL;DR

This paper introduces SPN, a strategy-aware method that adapts tabular foundation models to strategic data environments, improving robustness without retraining.

Contribution

It proposes a novel inference-time framework, SPN, that aligns foundation model predictions with strategic data distributions in real-world scenarios.

Findings

SPN improves robustness against strategic manipulation.

SPN outperforms classical tabular methods and foundation models.

Experiments validate SPN's effectiveness on real and synthetic datasets.

Abstract

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.