# Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections

arXiv: https://arxiv.org/abs/1810.02678 · HTML: https://mlsanity.com/paper/1810.02678/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2018.

## Built on by (most cited first, 10 of 10)

- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Deep Learning Approaches for Seizure Video Analysis: A Review](https://mlsanity.com/paper/2312.10930/) (2023)
- [LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations](https://mlsanity.com/paper/2111.08094/) (2021)
- [Integrating Prior Knowledge in Post-hoc Explanations](https://mlsanity.com/paper/2204.11634/) (2022)
- [Towards interpreting ML-based automated malware detection models: a survey](https://mlsanity.com/paper/2101.06232/) (2021)
- [ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI](https://mlsanity.com/paper/2110.11597/) (2021)
- [Causality-Aware Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2212.05256/) (2022)
- [Towards Interpretable Classification of Leukocytes based on Deep Learning](https://mlsanity.com/paper/2311.14485/) (2023)
- [Enhancing LIME using Neural Decision Trees](https://mlsanity.com/paper/2603.20919/) (2026)
- [A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification](https://mlsanity.com/paper/2605.21114/) (2026)

## Abstract (arXiv)

We introduce a method, KL-LIME, for explaining predictions of Bayesian predictive models by projecting the information in the predictive distribution locally to a simpler, interpretable explanation model. The proposed approach combines the recent Local Interpretable Model-agnostic Explanations (LIME) method with ideas from Bayesian projection predictive variable selection methods. The information theoretic basis helps in navigating the trade-off between explanation fidelity and complexity. We demonstrate the method in explaining MNIST digit classifications made by a Bayesian deep convolutional neural network.