mlsanityData to 14 Oct 2026

On Validating, Repairing and Refining Heuristic ML Explanations

arXiv 1907.02509 ↗First posted 4 Jul 2019cs.LG cs.AI cs.LOcited by 32

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions. For non-interpretable ML models, the most commonly used approaches for computing explanations are heuristic in nature. In contrast, recent work proposed rigorous approaches for computing explanations, which hold for a given ML model and prediction over the entire instance space. This paper extends earlier work to the case of boosted trees and assesses the quality of explanations obtained with state-of-the-art heuristic approaches. On most of the datasets considered, and for the vast majority of instances, the explanations obtained with heuristic approaches are shown to be inadequate when the entire instance space is (implicitly) considered.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 8; 2024: 3; 2025: 1; 2026: 6.

32 papers.

Sort:

  1. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  2. 2022Logic-Based Explainability in Machine Learningcited by 48
  3. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  4. 2022Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networkscited by 42
  5. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  6. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  7. 2021Provably efficient, succinct, and precise explanationscited by 32
  8. 2021Probabilistic Sufficient Explanationscited by 24
  9. 2023Formally Explaining Neural Networks within Reactive Systemscited by 24
  10. 2022On the Computation of Necessary and Sufficient Explanationscited by 23
  11. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  12. 2022Computing Abductive Explanations for Boosted Treescited by 23
20 more
  1. 2023Logic for Explainable AIcited by 23
  2. 2023Explainability is NOT a Gamecited by 23
  3. 2021On Quantifying Literals in Boolean Logic and Its Applications to Explainable AIcited by 16
  4. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12
  5. 2023Axiomatic Aggregations of Abductive Explanationscited by 10
  6. 2023A New Class of Explanations for Classifiers with Non-Binary Featurescited by 8
  7. 2025Formal Abductive Latent Explanations for Prototype-Based Networkscited by 5
  8. 2021Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification modelscited by 4
  9. 2023A Uniform Language to Explain Decision Treescited by 4
  10. 2021Sufficient reasons for classifier decisions in the presence of constraintscited by 3
  11. 2024Logic-based Explanations for Linear Support Vector Classifiers with Reject Optioncited by 3
  12. 2024Logic-Based Explainability: Past, Present & Futurecited by 2
  13. 2026Generalizing Logic-based Explanations for Machine Learning Classifiers via Optimizationcited by 2
  14. 2023The Shape of Explanations: A Topological Account of Rule-Based Explanations in Machine Learningcited by 1
  15. 2024Guarantee Regions for Local Explanationscited by 0
  16. 2026Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathycited by 0
  17. 2026Concisely Explaining the Doubt: Minimum-Size Abductive Explanations for Linear Models with a Reject Optioncited by 0
  18. 2026Scaling the Explanation of Multi-Class Bayesian Network Classifierscited by 0
  19. 2026Rigorous Explanations for Tree Ensemblescited by 0
  20. 2026Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Modelscited by 0