mlsanityData to 14 Oct 2026

Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae

arXiv 2509.09982 ↗First posted 12 Sep 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Evaluating explainable AI (XAI) approaches is a challenging task in general, due to the subjectivity of explanations. In this paper, we focus on tabular data and the specific use case of AI models predicting the values of Boolean functions. We extend the previous work in this domain by proposing a formal and precise measure of importance of variables based on actual causality, and we evaluate state-of-the-art XAI tools against this measure. We also present a novel XAI tool B-ReX, based on the existing tool ReX, and demonstrate that it is superior to other black-box XAI tools on a large-scale benchmark. Specifically, B-ReX achieves a Jensen-Shannon divergence of 0.072 ± 0.012 on random 10-valued Boolean formulae

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 12 Sep 2025.

Builds on

15 of 35 references.

References · 15

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  6. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  7. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  8. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  9. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  10. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
  11. 2019Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networkscited by 49
  12. 2020One Explanation is Not Enough: Structured Attention Graphs for Image Classificationcited by 32
3 more
  1. 2022Causal Explanations and XAIcited by 30
  2. 2021Causal Sufficiency and Actual Causationcited by 29
  3. 2019Efficiently Checking Actual Causality with SAT Solvingcited by 1

Built on by

Not cited yet.