Unifying VXAI: A Systematic Review and Framework for the Evaluation of Explainable AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dembinsky, David, Lucieri, Adriano, Frolov, Stanislav, Najjar, Hiba, Watanabe, Ko, Dengel, Andreas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914339341991936
author Dembinsky, David
Lucieri, Adriano
Frolov, Stanislav
Najjar, Hiba
Watanabe, Ko
Dengel, Andreas
author_facet Dembinsky, David
Lucieri, Adriano
Frolov, Stanislav
Najjar, Hiba
Watanabe, Ko
Dengel, Andreas
contents Modern AI systems frequently rely on opaque black-box models, most notably Deep Neural Networks, whose performance stems from complex architectures with millions of learned parameters. While powerful, their complexity poses a major challenge to trustworthiness, particularly due to a lack of transparency. Explainable AI (XAI) addresses this issue by providing human-understandable explanations of model behavior. However, to ensure their usefulness and trustworthiness, such explanations must be rigorously evaluated. Despite the growing number of XAI methods, the field lacks standardized evaluation protocols and consensus on appropriate metrics. To address this gap, we conduct a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and introduce a unified framework for the eValuation of XAI (VXAI). We identify 362 relevant publications and aggregate their contributions into 41 functionally similar metric groups. In addition, we propose a three-dimensional categorization scheme spanning explanation type, evaluation contextuality, and explanation quality desiderata. Our framework provides the most comprehensive and structured overview of VXAI to date. It supports systematic metric selection, promotes comparability across methods, and offers a flexible foundation for future extensions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unifying VXAI: A Systematic Review and Framework for the Evaluation of Explainable AI
Dembinsky, David
Lucieri, Adriano
Frolov, Stanislav
Najjar, Hiba
Watanabe, Ko
Dengel, Andreas
Machine Learning
Artificial Intelligence
Modern AI systems frequently rely on opaque black-box models, most notably Deep Neural Networks, whose performance stems from complex architectures with millions of learned parameters. While powerful, their complexity poses a major challenge to trustworthiness, particularly due to a lack of transparency. Explainable AI (XAI) addresses this issue by providing human-understandable explanations of model behavior. However, to ensure their usefulness and trustworthiness, such explanations must be rigorously evaluated. Despite the growing number of XAI methods, the field lacks standardized evaluation protocols and consensus on appropriate metrics. To address this gap, we conduct a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and introduce a unified framework for the eValuation of XAI (VXAI). We identify 362 relevant publications and aggregate their contributions into 41 functionally similar metric groups. In addition, we propose a three-dimensional categorization scheme spanning explanation type, evaluation contextuality, and explanation quality desiderata. Our framework provides the most comprehensive and structured overview of VXAI to date. It supports systematic metric selection, promotes comparability across methods, and offers a flexible foundation for future extensions.
title Unifying VXAI: A Systematic Review and Framework for the Evaluation of Explainable AI
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.15408