A Human-Centered Validation of the Explainability-Performance Coefficient

2026-07-31

AI Summary

This work addresses a central challenge in explainable artificial intelligence (XAI): objectively evaluating the fidelity of explanations and aligning them with human understanding. The authors propose EPC, a model-agnostic scoring metric that quantifies explanation quality by jointly optimizing feature sparsity and preservation of model performance. For the first time, the method validates automatically generated explanations against human-provided semantic sentiment judgments and visual spatial annotations across multimodal data—including tabular, textual, and image domains—demonstrating strong alignment. Experiments show that the EPC score not only effectively reveals dependencies between explainer performance and factors such as network activations and data dimensionality but also exhibits high correlation with human-centered evaluations, thereby establishing a reliable and generalizable paradigm for XAI assessment.

Abstract

The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). However, objectively evaluating explanation fidelity and aligning XAI metrics with human-centered understanding remain critical open challenges. In this work, we propose a model-agnostic metric, the EPC score, which is an extension of the Explainability-Performance Coefficient (EPC), that quantifies explanation quality by explicitly balancing the trade-off between feature selection sparsity and preserved model performance. Through an empirical validation across tabular, text, and image modalities, we show that the EPC score effectively uncovers operational dependencies among network activations, data dimensionality, and explainer performance. Furthermore, we validate the EPC score against independent human-based explanations, proving that higher EPC scores strongly align with human lexical sentiment judgments and spatial visual annotations.

Problem

• Explainable Artificial Intelligence
• explanation fidelity
• human-centered evaluation
• XAI metrics
• trustworthy AI

Innovation

• Explainable AI
• EPC score
• human-centered validation
• model-agnostic metric
• explanation fidelity