What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks

Abstract

Despite significant progress, evaluation of explainable artificial intelligence remains elusive and challenging. In this paper we propose a fine-grained validation framework that is not overly reliant on any one facet of these sociotechnical systems, and that recognises their inherent modular structure: technical building blocks, user-facing explanatory artefacts and social communication protocols. While we concur that user studies are invaluable in assessing the quality and effectiveness of explanation presentation and delivery strategies from the explainees' perspective in a particular deployment context, the underlying explanation generation mechanisms require a separate, predominantly algorithmic validation strategy that accounts for the technical and human-centred desiderata of their (numerical) outputs. Such a comprehensive sociotechnical utility-based evaluation framework could allow to systematically reason about the properties and downstream influence of different building blocks from which explainable artificial intelligence systems are composed -- accounting for a diverse range of their engineering and social aspects -- in view of the anticipated use case.

arXiv commentPublished in Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems (CHI EA '24)

References in corpus (15)

• Interpretable machine learning: definitions, methods, and applications
• Explainable Machine Learning for Scientific Insights and Discoveries
• The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanations
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• The Pragmatic Turn in Explainable Artificial Intelligence (XAI)
• XFake: Explainable Fake News Detector with Visualizations
• How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations
• OpenXAI: Towards a Transparent Evaluation of Model Explanations
• Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI
• Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory
• Towards a Comprehensive Human-Centred Evaluation Framework for Explainable AI

Cited by in corpus (5)

• Interpretable Representations in Explainable AI: From Theory to Practice
• Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations
• LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
• Leveraging Complementary AI Explanations to Mitigate Misunderstanding in XAI
• Navigating Explanatory Multiverse Through Counterfactual Path Geometry