# Real-Time Explanations for Tabular Foundation Models

arXiv: https://arxiv.org/abs/2603.29946 · HTML: https://mlsanity.com/paper/2603.29946/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN](https://mlsanity.com/paper/2511.03634/) (2025)
- [Interpretable Machine Learning for Weather and Climate Prediction: A Survey](https://mlsanity.com/paper/2403.18864/) (2024)
- [Prediction via Shapley Value Regression](https://mlsanity.com/paper/2505.04775/) (2025)

## Abstract (arXiv)

Interpretability is central for scientific machine learning, as understanding 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 (R2=0.96, cosine=0.99) over 1000× faster than KernelSHAP (0.06s vs 610s). Our code is available at https://github.com/kunumi/ShapPFN