# Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME

arXiv: https://arxiv.org/abs/1808.00629 · HTML: https://mlsanity.com/paper/1808.00629/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Generating Explainable Rule Sets from Tree-Ensemble Learning Methods by Answer Set Programming](https://mlsanity.com/paper/2109.08290/) (2021)
- [Towards Dynamic Consistency Checking in Goal-directed Predicate Answer Set Programming](https://mlsanity.com/paper/2110.12053/) (2021)
- [Generating Global and Local Explanations for Tree-Ensemble Learning Methods by Answer Set Programming](https://mlsanity.com/paper/2410.11000/) (2024)
- [A Survey of the Various Methodologies Towards making Artificial Intelligence More Explainable](https://mlsanity.com/paper/2311.02291/) (2023)
- [Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach](https://mlsanity.com/paper/2604.06838/) (2026)

## Abstract (arXiv)

We present a heuristic based algorithm to induce textitnonmonotonic logic programs that will explain the behavior of XGBoost trained classifiers. We use the technique based on the LIME approach to locally select the most important features contributing to the classification decision. Then, in order to explain the model's global behavior, we propose the LIME-FOLD algorithm ---a heuristic-based inductive logic programming (ILP) algorithm capable of learning non-monotonic logic programs---that we apply to a transformed dataset produced by LIME. Our proposed approach is agnostic to the choice of the ILP algorithm. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics. Meanwhile, the number of induced rules dramatically decreases compared to ALEPH, a state-of-the-art ILP system.