Real-Time Explanations for Tabular Foundation Models
Luan Borges Teodoro Reis Sena, Francisco Galuppo Azevedo
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 e…
Cited by
- Kunumicites the paper in its model or dataset cards