mlsanityData to 7 Oct 2026

Three Modern Roles for Logic in AI

arXiv 2004.08599 ↗First posted 18 Apr 2020cs.AI cs.LG cs.LOcited by 15

Not on the map. Why?

Abstract (arXiv)

We consider three modern roles for logic in artificial intelligence, which are based on the theory of tractable Boolean circuits: (1) logic as a basis for computation, (2) logic for learning from a combination of data and knowledge, and (3) logic for reasoning about the behavior of machine learning systems.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 6; 2023: 1; 2024: 3.

15 papers.

Sort:

  1. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  2. 2022Logic-Based Explainability in Machine Learningcited by 47
  3. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  4. 2022ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanationscited by 26
  5. 2023Logic for Explainable AIcited by 23
  6. 2024Contestable AI needs Computational Argumentationcited by 12
  7. 2022Tractable Boolean and Arithmetic Circuitscited by 9
  8. 2022Cardinality-Minimal Explanations for Monotonic Neural Networkscited by 8
  9. 2021Adversarial Robustness Guarantees for Gaussian Processescited by 5
  10. 2021Sufficient reasons for classifier decisions in the presence of constraintscited by 3
  11. 2024Logic-Based Explainability: Past, Present & Futurecited by 2
  12. 2021Design of quantum optical experiments with logic artificial intelligencecited by 1
3 more
  1. 2021Exact Learning Augmented Naive Bayes Classifiercited by 0
  2. 2022A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumerationcited by 0
  3. 2024Modeling and Discovering Direct Causes for Predictive Modelscited by 0