Real-Time Explanations for Tabular Foundation Models
Abstract
Interpretability is central for scientific machine learning, as understanding \emph{why} models make predictions enables hypothesis generation and validation. While tabular foundation models show strong performance, existing explanation methods like SHAP are computationally expensive, limiting interactive exploration. We introduce ShapPFN, a foundation model that integrates Shapley value regression directly into its architecture, producing both predictions and explanations in a single forward pass. On standard benchmarks, ShapPFN achieves competitive performance while producing high-fidelity explanations (=0.96, cosine=0.99) over 1000\times faster than KernelSHAP (0.06s vs 610s). Our code is available at https://github.com/kunumi/ShapPFN
Cite
@article{arxiv.2603.29946,
title = {Real-Time Explanations for Tabular Foundation Models},
author = {Luan Borges Teodoro Reis Sena and Francisco Galuppo Azevedo},
journal= {arXiv preprint arXiv:2603.29946},
year = {2026}
}
Comments
Accepted at the 2nd DATA4Science Workshop at ICLR 2026, Rio de Janeiro, Brazil. OpenReview: https://openreview.net/forum?id=StSMBSZqxx