Logo image
Back
Measuring Interpretability: An Investigation of Domain Independent Interpretability
Conference proceeding

Measuring Interpretability: An Investigation of Domain Independent Interpretability

Prateek Goel and Rosina O Weber
2025 IEEE 6th International Conference on Pattern Recognition and Machine Learning (PRML), pp 276-284
13 Jun 2025
DOI: https://doi.org/10.1109/PRML66062.2025.11160328

Abstract

case-based reasoning Cognition Computational modeling Decision trees Deep learning Interpretability measurement Neural networks Pattern Recognition
Interpretability and explainability share the connotation of characterizing information that artificial intelligence (AI) models can provide for humans. They differ in that interpretability refers to information produced from inherent properties of AI models whereas explainability refers to what humans absorb from said information. Previous work suggests that information that may be used in lieu of explainability be evaluated for computational quality before it is made available for human studies to evaluate explainability. Measurement is a precondition for evaluation, therefore this paper investigates approaches proposed to measure aspects relevant for interpretability of the information that AI models produce. The goal is to evaluate, from a computational perspective, the quality of information models provide. The benefit of such evaluations would be the ability to provide valuable feedback to improve their quality. The resulting information could then be offered for user studies in different domains and applications. To validate interpretability, we rely on two concepts that reflect consensual notions, namely, those that compare models such as deep learning is less interpretable than decision trees and that the number of features is inversely proportional to interpretability.

Metrics

2 Record Views

Details

Logo image