mlsanityData to 7 Oct 2026

A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI)

arXiv 2307.14246 ↗First posted 26 Jul 2023cs.AI cs.SEcited by 5

Not on the map. Why?

Abstract (arXiv)

Within the field of Requirements Engineering (RE), the increasing significance of Explainable Artificial Intelligence (XAI) in aligning AI-supported systems with user needs, societal expectations, and regulatory standards has garnered recognition. In general, explainability has emerged as an important non-functional requirement that impacts system quality. However, the supposed trade-off between explainability and performance challenges the presumed positive influence of explainability. If meeting the requirement of explainability entails a reduction in system performance, then careful consideration must be given to which of these quality aspects takes precedence and how to compromise between them. In this paper, we critically examine the alleged trade-off. We argue that it is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk. By providing a foundation for future research and best practices, this work aims to advance the field of RE for AI.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 31 of its 73 references that are in the map. First posted on arXiv 26 Jul 2023.

Builds on

31 of 73 references.

References · 31

  1. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  3. 2018Sanity Checks for Saliency Mapscited by 1,149
  4. 2017Interpretation of Neural Networks is Fragilecited by 443
  5. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  6. 2017The (Un)reliability of saliency methodscited by 331
  7. 2018On the Robustness of Interpretability Methodscited by 310
  8. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  9. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  10. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  11. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 202
  12. 2020Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AIcited by 166
19 more
  1. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  2. 2021What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Researchcited by 119
  3. 2020Principles and Practice of Explainable Machine Learningcited by 99
  4. 2019Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AIcited by 63
  5. 2019Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanationscited by 63
  6. 2016"What is Relevant in a Text Document?": An Interpretable Machine Learning Approachcited by 53
  7. 2020The Pragmatic Turn in Explainable Artificial Intelligence (XAI)cited by 53
  8. 2018Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Valuescited by 40
  9. 2016Explaining Predictions of Non-Linear Classifiers in NLPcited by 37
  10. 2018Human-in-the-Loop Interpretability Priorcited by 35
  11. 2019Explainability in Human-Agent Systemscited by 34
  12. 2021Principles of Explanation in Human-AI Systemscited by 25
  13. 2015Analyzing Classifiers: Fisher Vectors and Deep Neural Networkscited by 24
  14. 2021Exploring Explainability: A Definition, a Model, and a Knowledge Cataloguecited by 15
  15. 2021Developing a Fidelity Evaluation Approach for Interpretable Machine Learningcited by 8
  16. 2021Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectivescited by 7
  17. 2017InterpNET: Neural Introspection for Interpretable Deep Learningcited by 5
  18. 2019Towards a Framework Combining Machine Ethics and Machine Explainabilitycited by 5
  19. 2022How to Evaluate Explainability? -- A Case for Three Criteriacited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 2.

5 papers.

  1. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  2. 2024Position: Explain to Question not to Justifycited by 20
  3. 2024What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blockscited by 6
  4. 2025Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency mapscited by 4
  5. 2025Evaluating Scenario-based Decision-making for Interactive Autonomous Driving Using Rational Criteria: A Surveycited by 1