# Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment

arXiv: https://arxiv.org/abs/2511.21931 · HTML: https://mlsanity.com/paper/2511.21931/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 6 of 6)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [The Effects of Data Quality on Machine Learning Performance on Tabular Data](https://mlsanity.com/paper/2207.14529/) (2022)

## Abstract (arXiv)

In this work, we propose a simple and computationally efficient framework for evaluating whether machine learning models align with the structure of the data they learn from; that is, whether the model says what the data says. Unlike existing interpretability methods that focus exclusively on explaining model behavior, our approach establishes a baseline derived directly from the data itself. Drawing inspiration from Rubin's Potential Outcomes Framework, we quantify how strongly each feature separates the two outcome groups in a binary classification task, moving beyond traditional descriptive statistics to estimate each feature's effect on the outcome. By comparing these data-derived feature rankings with model-based explanations, we provide practitioners with an interpretable and model-agnostic method for assessing model-data alignment.