mlsanityData to 7 Oct 2026

Is Task-Agnostic Explainable AI a Myth?

arXiv 2307.06963 ↗First posted 13 Jul 2023cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Our work serves as a framework for unifying the challenges of contemporary explainable AI (XAI). We demonstrate that while XAI methods provide supplementary and potentially useful output for machine learning models, researchers and decision-makers should be mindful of their conceptual and technical limitations, which frequently result in these methods themselves becoming black boxes. We examine three XAI research avenues spanning image, textual, and graph data, covering saliency, attention, and graph-type explainers. Despite the varying contexts and timeframes of the mentioned cases, the same persistent roadblocks emerge, highlighting the need for a conceptual breakthrough in the field to address the challenge of compatibility between XAI methods and application tasks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 48 of its 70 references that are in the map. First posted on arXiv 13 Jul 2023.

Builds on

48 of 70 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  10. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  11. 2018Sanity Checks for Saliency Mapscited by 1,149
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,097
36 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  2. 2019Attention is not Explanationcited by 916
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  4. 2019Attention is not not Explanationcited by 629
  5. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  6. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  7. 2019Is Attention Interpretable?cited by 387
  8. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  9. 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
  10. 2017The (Un)reliability of saliency methodscited by 331
  11. 2018On the Robustness of Interpretability Methodscited by 310
  12. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  13. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 231
  14. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  15. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  16. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156
  17. 2019What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Usecited by 134
  18. 2019Sanity Checks for Saliency Metricscited by 119
  19. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  20. 2022Explanations Can Reduce Overreliance on AI Systems During Decision-Makingcited by 111
  21. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  22. 2022Evaluating Explainability for Graph Neural Networkscited by 85
  23. 2022Impossibility Theorems for Feature Attributioncited by 78
  24. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  25. 2019Attention Interpretability Across NLP Taskscited by 71
  26. 2021How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanationscited by 58
  27. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  28. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  29. 2020Towards Transparent and Explainable Attention Modelscited by 47
  30. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  31. 2021Order in the Court: Explainable AI Methods Prone to Disagreementcited by 36
  32. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  33. 2021Revisiting Sanity Checks for Saliency Mapscited by 20
  34. 2022Use-Case-Grounded Simulations for Explanation Evaluationcited by 19
  35. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  36. 2018A Feature Selection Method Based on Shapley Value to False Alarm Reduction in ICUs, A Genetic-Algorithm Approachcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?cited by 2