mlsanityData to 14 Oct 2026

The Disagreement Problem in Faithfulness Metrics

arXiv 2311.07763 ↗First posted 13 Nov 2023cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-hoc feature attributions to any model architecture. While the pace of innovation around novel methods has slowed down, the question remains of how to choose a method, and how to make it fit for purpose. Recently, efforts around benchmarking XAI methods have suggested metrics for that purpose -- but there are many choices. That bounty of choice still leaves an end user unclear on how to proceed. This paper focuses on comparing metrics with the aim of measuring faithfulness of local explanations on tabular classification problems -- and shows that the current metrics don't agree; leaving users unsure how to choose the most faithful explanations.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 13 Nov 2023.

Builds on

19 of 27 references.

References · 19

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  5. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  6. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  7. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  8. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  9. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  10. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 159
  11. 2022Scaling Laws and Interpretability of Learning from Repeated Datacited by 152
  12. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 126
7 more
  1. 2019Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importancecited by 87
  2. 2015The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classificationcited by 76
  3. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
  4. 2021On Baselines for Local Feature Attributionscited by 29
  5. 2021Counterfactual Shapley Additive Explanationscited by 22
  6. 2017Statistical Analysis and Parameter Selection for Mappercited by 20
  7. 2022BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligencecited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  2. 2025Evaluating Model Explanations without Ground Truthcited by 7
  3. 2025Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoMLcited by 6
  4. 2024A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learningcited by 2
  5. 2025Additive Large Language Models for Semi-Structured Textcited by 0
  6. 2026Attribution Upsampling should Redistribute, Not Interpolatecited by 0