mlsanityData to 7 Oct 2026

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

arXiv 2403.12730 ↗First posted 19 Mar 2024cs.HC cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 85 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

42 of 85 references.

References · 42

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  3. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  4. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  5. 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
  6. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  7. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  8. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 165
  9. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  10. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  11. 2021What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Researchcited by 119
  12. 2019Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approachescited by 101
30 more
  1. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  2. 2020The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategiescited by 91
  3. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  4. 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
  5. 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 71
  6. 2019An Evaluation of the Human-Interpretability of Explanationcited by 71
  7. 2020On quantitative aspects of model interpretabilitycited by 71
  8. 2020One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparencycited by 64
  9. 2019Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanationscited by 63
  10. 2021How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanationscited by 58
  11. 2020The Pragmatic Turn in Explainable Artificial Intelligence (XAI)cited by 53
  12. 2017The Promise and Peril of Human Evaluation for Model Interpretabilitycited by 52
  13. 2018Stakeholders in Explainable AIcited by 48
  14. 2018Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systemscited by 47
  15. 2022Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AIcited by 40
  16. 2019Explainability in Human-Agent Systemscited by 34
  17. 2023Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAIcited by 33
  18. 2019XFake: Explainable Fake News Detector with Visualizationscited by 32
  19. 2022Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theorycited by 32
  20. 2021Principles of Explanation in Human-AI Systemscited by 25
  21. 2019bLIMEy: Surrogate Prediction Explanations Beyond LIMEcited by 17
  22. 2020A multi-component framework for the analysis and design of explainable artificial intelligencecited by 14
  23. 2021Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputscited by 9
  24. 2020LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classescited by 8
  25. 2023Mind the Gap! Bridging Explainable Artificial Intelligence and Human Understanding with Luhmann's Functional Theory of Communicationcited by 7
  26. 2023(Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibilitycited by 6
  27. 2023A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI)cited by 5
  28. 2021Explanatory Pluralism in Explainable AIcited by 4
  29. 2022What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Componentscited by 3
  30. 2023Helpful, Misleading or Confusing: How Humans Perceive Fundamental Building Blocks of Artificial Intelligence Explanationscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025LLMs for Explainable AI: A Comprehensive Surveycited by 42
  2. 2025Uncertainty Quantification as a Principled Foundation for Explainable Artificial Intelligence: A Case Study of Counterfactual Explanationscited by 2
  3. 2026Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methodscited by 2
  4. 2026Textual Explanations and Their Evaluations for Reinforcement Learning Policycited by 0
  5. 2026Emergent, not Immanent: A Baradian Reading of Explainable AIcited by 0
  6. 2026XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?cited by 0