# Three Modern Roles for Logic in AI

arXiv: https://arxiv.org/abs/2004.08599 · HTML: https://mlsanity.com/paper/2004.08599/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2020.

## Built on by (most cited first, 15 of 15)

- [On Guaranteed Optimal Robust Explanations for NLP Models](https://mlsanity.com/paper/2105.03640/) (2021)
- [Logic-Based Explainability in Machine Learning](https://mlsanity.com/paper/2211.00541/) (2022)
- [On Tackling Explanation Redundancy in Decision Trees](https://mlsanity.com/paper/2205.09971/) (2022)
- [ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanations](https://mlsanity.com/paper/2206.11900/) (2022)
- [Logic for Explainable AI](https://mlsanity.com/paper/2305.05172/) (2023)
- [Contestable AI needs Computational Argumentation](https://mlsanity.com/paper/2405.10729/) (2024)
- [Tractable Boolean and Arithmetic Circuits](https://mlsanity.com/paper/2202.02942/) (2022)
- [Cardinality-Minimal Explanations for Monotonic Neural Networks](https://mlsanity.com/paper/2205.09901/) (2022)
- [Adversarial Robustness Guarantees for Gaussian Processes](https://mlsanity.com/paper/2104.03180/) (2021)
- [Sufficient reasons for classifier decisions in the presence of constraints](https://mlsanity.com/paper/2105.06001/) (2021)
- [Logic-Based Explainability: Past, Present & Future](https://mlsanity.com/paper/2406.11873/) (2024)
- [Design of quantum optical experiments with logic artificial intelligence](https://mlsanity.com/paper/2109.13273/) (2021)
- [Exact Learning Augmented Naive Bayes Classifier](https://mlsanity.com/paper/2107.03018/) (2021)
- [A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumeration](https://mlsanity.com/paper/2206.11539/) (2022)
- [Modeling and Discovering Direct Causes for Predictive Models](https://mlsanity.com/paper/2412.02878/) (2024)

## 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.