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

📅 2025-11-26
📈 Citations: 0
Influential: 0
📄 PDF

career value

197K/year
🤖 AI Summary
Existing interpretability methods lack standardized data benchmarks and struggle to assess whether model explanations genuinely reflect the intrinsic structure of training data. Method: We propose a model-agnostic framework for evaluating model-data consistency, grounded in Rubin’s potential outcomes framework to construct a model-free, data-driven baseline. This baseline quantifies the true separative effect of each feature on binary classification tasks. Model explanations are then diagnosed by comparing feature importance rankings against this causal, data-derived baseline. Contribution/Results: Our approach efficiently detects when models deviate from fundamental data-generating mechanisms. It offers strong interpretability, low computational overhead, and cross-model applicability. To our knowledge, it is the first causally grounded, feature-effect-based tool for validating model-data consistency—providing a foundational method for trustworthy AI evaluation.

Technology Category

Application Category

📝 Abstract
In this work, we propose a simple and computationally efficient framework to evaluate whether machine learning models align with the structure of the data they learn from; that is, whether extit{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 against model-based explanations, we provide practitioners with an interpretable and model-agnostic method to assess model--data alignment.
Problem

Research questions and friction points this paper is trying to address.

Evaluates model alignment with data structure
Compares data-derived feature rankings to model explanations
Provides model-agnostic method for alignment assessment
Innovation

Methods, ideas, or system contributions that make the work stand out.

Framework compares model explanations with data-derived feature rankings
Uses Rubin's Potential Outcomes Framework to quantify feature effects
Provides model-agnostic method for assessing model-data alignment
H
Henry Salgado
Department of Computer Science, The University of Texas at El Paso, El Paso, TX, USA
M
Meagan Kendall
Department of Engineering Education and Leadership, The University of Texas at El Paso, El Paso, TX, USA
M
Martine Ceberio
Department of Computer Science, The University of Texas at El Paso, El Paso, TX, USA