Salvato in:
Dettagli Bibliografici
Autori principali: Salgado, Henry, Kendall, Meagan R., Ceberio, Martine
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.21931
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918458301612032
author Salgado, Henry
Kendall, Meagan R.
Ceberio, Martine
author_facet Salgado, Henry
Kendall, Meagan R.
Ceberio, Martine
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21931
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment
Salgado, Henry
Kendall, Meagan R.
Ceberio, Martine
Machine Learning
Artificial Intelligence
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.
title Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.21931