mlsanityData to 7 Oct 2026

Challenges in Evaluating Explanation Methods for Static and Evolving Data

arXiv 2608.06351 ↗First posted 6 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through the DetoxAI image recognition system for bias detection and concept unlearning. Then, an example of a human-grounded evaluation of methods for explaining image classification is presented. The paper further explores methods for adapting explanations to evolving data streams with concept drift. Experiences with adapting counterfactuals for this problem are discussed. Finally it is related to the challenges of tracking the co-evolution of data, models, and explanations.footnoteThis paper has been accepted for a publication in J.Nalepa (ed) Explainable AI in Space. Proceedings of EASi 2026 Workshop at IJCAI-ECAI 2026 Bremen, Springer CCIS vol 3107 (2016).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 6 Aug 2026.

Builds on

16 of 32 references.

References · 16

  1. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  2. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  3. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  4. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  6. 2020Learning under Concept Drift: A Reviewcited by 470
  7. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  8. 2020GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learningcited by 50
  9. 2023Model Based Explanations of Concept Driftcited by 19
  10. 2024Probabilistically Plausible Counterfactual Explanations with Normalizing Flowscited by 11
  11. 2024A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainerscited by 7
  12. 2024GLANCE: Global Actions in a Nutshell for Counterfactual Explainabilitycited by 6
4 more
  1. 2022Learning from Data Streams: An Overview and Updatecited by 5
  2. 2025Explaining Concept Drift through the Evolution of Group Counterfactualscited by 2
  3. 2026Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methodscited by 2
  4. 2025DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Visioncited by 1

Built on by

Not cited yet.