mlsanityData to 14 Oct 2026

Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution

arXiv 2502.15403 ↗First posted 21 Feb 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Obtaining high-quality explanations of a model's output enables developers to identify and correct biases, align the system's behavior with human values, and ensure ethical compliance. Explainable Artificial Intelligence (XAI) practitioners rely on specific measures to gauge the quality of such explanations. These measures assess key attributes, such as how closely an explanation aligns with a model's decision process (faithfulness), how accurately it pinpoints the relevant input features (localization), and its consistency across different cases (robustness). Despite providing valuable information, these measures do not fully address a critical practitioner's concern: how does the quality of a given explanation compare to other potential explanations? Traditionally, the quality of an explanation has been assessed by comparing it to a randomly generated counterpart. This paper introduces an alternative: the Quality Gap Estimate (QGE). The QGE method offers a direct comparison to what can be viewed as the `inverse' explanation, one that conceptually represents the antithesis of the original explanation. Our extensive testing across multiple model architectures, datasets, and established quality metrics demonstrates that the QGE method is superior to the traditional approach. Furthermore, we show that QGE enhances the statistical reliability of these quality assessments. This advance represents a significant step toward a more insightful evaluation of explanations that enables a more effective inspection of a model's behavior.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

17 of 29 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  5. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  6. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 188
  7. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  8. 2020Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAIcited by 126
  9. 2019Sanity Checks for Saliency Metricscited by 119
  10. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 102
  11. 2020On quantitative aspects of model interpretabilitycited by 71
  12. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
5 more
  1. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  2. 2020IROF: a low resource evaluation metric for explanation methodscited by 46
  3. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  4. 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 27
  5. 2021Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparisoncited by 7

Built on by

Not cited yet.