mlsanityData to 14 Oct 2026

On The Reasons Behind Decisions

arXiv 2002.09284 ↗First posted 21 Feb 2020cs.AI cs.LGcited by 100

Not on the map. Why?

Abstract (arXiv)

Recent work has shown that some common machine learning classifiers can be compiled into Boolean circuits that have the same input-output behavior. We present a theory for unveiling the reasons behind the decisions made by Boolean classifiers and study some of its theoretical and practical implications. We define notions such as sufficient, necessary and complete reasons behind decisions, in addition to classifier and decision bias. We show how these notions can be used to evaluate counterfactual statements such as "a decision will stick even if ... because ... ." We present efficient algorithms for computing these notions, which are based on new advances on tractable Boolean circuits, and illustrate them using a case study.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 14; 2023: 13; 2024: 13; 2025: 18; 2026: 20.

100 papers.

Sort:

By area:

  1. 2021Argumentative XAI: A Surveycited by 67
  2. 2021On Explaining Random Forests with SATcited by 57
  3. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  4. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  5. 2022Logic-Based Explainability in Machine Learningcited by 48
  6. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  7. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  8. 2021On the Computational Intelligibility of Boolean Classifierscited by 40
  9. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  10. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  11. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  12. 2021Trading Complexity for Sparsity in Random Forest Explanationscited by 32
38 more
  1. 2021Provably efficient, succinct, and precise explanationscited by 32
  2. 2023The Inadequacy of Shapley Values for Explainabilitycited by 31
  3. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  4. 2022Causal Explanations and XAIcited by 30
  5. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  6. 2021Foundations of Symbolic Languages for Model Interpretabilitycited by 26
  7. 2021Probabilistic Sufficient Explanationscited by 24
  8. 2022On the Computation of Necessary and Sufficient Explanationscited by 23
  9. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  10. 2022Computing Abductive Explanations for Boosted Treescited by 23
  11. 2023Logic for Explainable AIcited by 23
  12. 2024Local vs. Global Interpretability: A Computational Complexity Perspectivecited by 23
  13. 2022On Computing Probabilistic Abductive Explanationscited by 18
  14. 2023SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]cited by 18
  15. 2021On Quantifying Literals in Boolean Logic and Its Applications to Explainable AIcited by 16
  16. 2021A unified logical framework for explanations in classifier systemscited by 15
  17. 2025Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanationscited by 13
  18. 2021Efficient Explanations With Relevant Setscited by 12
  19. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  20. 2023On Formal Feature Attribution and Its Approximationcited by 11
  21. 2024Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretationcited by 11
  22. 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guaranteescited by 11
  23. 2021Efficient Explanations for Knowledge Compilation Languagescited by 10
  24. 2023Language Models as a Service: Overview of a New Paradigm and its Challengescited by 10
  25. 2025Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanationscited by 10
  26. 2022Tractable Boolean and Arithmetic Circuitscited by 9
  27. 2022Provably Precise, Succinct and Efficient Explanations for Decision Treescited by 8
  28. 2023A New Class of Explanations for Classifiers with Non-Binary Featurescited by 8
  29. 2025SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelismcited by 8
  30. 2024Abductive explanations of classifiers under constraints: Complexity and propertiescited by 7
  31. 2021On the Explanatory Power of Decision Treescited by 6
  32. 2024Why do explanations fail? A typology and discussion on failures in XAIcited by 6
  33. 2022On Computing Relevant Features for Explaining NBCscited by 5
  34. 2023On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuitscited by 5
  35. 2025Self-Explaining Neural Networks for Business Process Monitoringcited by 5
  36. 2021Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification modelscited by 4
  37. 2023A Uniform Language to Explain Decision Treescited by 4
  38. 2024Efficiently Computing Compact Formal Explanationscited by 4

50 most cited of 100 All 100 (JSON)