# On Validating, Repairing and Refining Heuristic ML Explanations

arXiv: https://arxiv.org/abs/1907.02509 · HTML: https://mlsanity.com/paper/1907.02509/

## Key facts

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

## Built on by (most cited first, 30 of 32)

- [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)
- [Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networks](https://mlsanity.com/paper/2210.13915/) (2022)
- [SAT-Based Rigorous Explanations for Decision Lists](https://mlsanity.com/paper/2105.06782/) (2021)
- [On Efficiently Explaining Graph-Based Classifiers](https://mlsanity.com/paper/2106.01350/) (2021)
- [Provably efficient, succinct, and precise explanations](https://mlsanity.com/paper/2111.01576/) (2021)
- [Probabilistic Sufficient Explanations](https://mlsanity.com/paper/2105.10118/) (2021)
- [Formally Explaining Neural Networks within Reactive Systems](https://mlsanity.com/paper/2308.00143/) (2023)
- [On the Computation of Necessary and Sufficient Explanations](https://mlsanity.com/paper/2203.10451/) (2022)
- [Eliminating The Impossible, Whatever Remains Must Be True](https://mlsanity.com/paper/2206.09551/) (2022)
- [Computing Abductive Explanations for Boosted Trees](https://mlsanity.com/paper/2209.07740/) (2022)
- [Logic for Explainable AI](https://mlsanity.com/paper/2305.05172/) (2023)
- [Explainability is NOT a Game](https://mlsanity.com/paper/2307.07514/) (2023)
- [On Quantifying Literals in Boolean Logic and Its Applications to Explainable AI](https://mlsanity.com/paper/2108.09876/) (2021)
- [Disproving XAI Myths with Formal Methods -- Initial Results](https://mlsanity.com/paper/2306.01744/) (2023)
- [Axiomatic Aggregations of Abductive Explanations](https://mlsanity.com/paper/2310.03131/) (2023)
- [A New Class of Explanations for Classifiers with Non-Binary Features](https://mlsanity.com/paper/2304.14760/) (2023)
- [Formal Abductive Latent Explanations for Prototype-Based Networks](https://mlsanity.com/paper/2511.16588/) (2025)
- [Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models](https://mlsanity.com/paper/2111.04658/) (2021)
- [A Uniform Language to Explain Decision Trees](https://mlsanity.com/paper/2310.11636/) (2023)
- [Sufficient reasons for classifier decisions in the presence of constraints](https://mlsanity.com/paper/2105.06001/) (2021)
- [Logic-based Explanations for Linear Support Vector Classifiers with Reject Option](https://mlsanity.com/paper/2403.16190/) (2024)
- [Logic-Based Explainability: Past, Present & Future](https://mlsanity.com/paper/2406.11873/) (2024)
- [Generalizing Logic-based Explanations for Machine Learning Classifiers via Optimization](https://mlsanity.com/paper/2603.01870/) (2026)
- [The Shape of Explanations: A Topological Account of Rule-Based Explanations in Machine Learning](https://mlsanity.com/paper/2301.09042/) (2023)
- [Guarantee Regions for Local Explanations](https://mlsanity.com/paper/2402.12737/) (2024)
- [Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy](https://mlsanity.com/paper/2602.22288/) (2026)
- [Concisely Explaining the Doubt: Minimum-Size Abductive Explanations for Linear Models with a Reject Option](https://mlsanity.com/paper/2603.14096/) (2026)
- [Scaling the Explanation of Multi-Class Bayesian Network Classifiers](https://mlsanity.com/paper/2603.14594/) (2026)

## 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.