# S-LIME: Stabilized-LIME for Model Explanation

arXiv: https://arxiv.org/abs/2106.07875 · HTML: https://mlsanity.com/paper/2106.07875/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 60 references that are in the map.
- First posted on arXiv 15 Jun 2021.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning](https://mlsanity.com/paper/2012.09816/) (2020)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Fairwashing: the risk of rationalization](https://mlsanity.com/paper/1901.09749/) (2019)
- [DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems](https://mlsanity.com/paper/1906.10263/) (2019)
- [Interpretable Classification Models for Recidivism Prediction](https://mlsanity.com/paper/1503.07810/) (2015)
- [False Discoveries Occur Early on the Lasso Path](https://mlsanity.com/paper/1511.01957/) (2015)
- [Unbiased Measurement of Feature Importance in Tree-Based Methods](https://mlsanity.com/paper/1903.05179/) (2019)
- [OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms](https://mlsanity.com/paper/2006.05714/) (2020)
- [Why distillation helps: a statistical perspective](https://mlsanity.com/paper/2005.10419/) (2020)
- [An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection](https://mlsanity.com/paper/1708.05894/) (2017)
- [Early detection of sepsis utilizing deep learning on electronic health record event sequences](https://mlsanity.com/paper/1906.02956/) (2019)
- [Improving LIME Robustness with Smarter Locality Sampling](https://mlsanity.com/paper/2006.12302/) (2020)
- [Approximation Trees: Statistical Stability in Model Distillation](https://mlsanity.com/paper/1808.07573/) (2018)
- [When Is the First Spurious Variable Selected by Sequential Regression Procedures?](https://mlsanity.com/paper/1708.03046/) (2017)

## Built on by (most cited first, 30 of 52)

- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [GLIME: General, Stable and Local LIME Explanation](https://mlsanity.com/paper/2311.15722/) (2023)
- [Calibrated Explanations: with Uncertainty Information and Counterfactuals](https://mlsanity.com/paper/2305.02305/) (2023)
- [Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set](https://mlsanity.com/paper/2110.13369/) (2021)
- [Motif-guided Time Series Counterfactual Explanations](https://mlsanity.com/paper/2211.04411/) (2022)
- [M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps](https://mlsanity.com/paper/2411.02649/) (2024)
- [ControlBurn: Feature Selection by Sparse Forests](https://mlsanity.com/paper/2107.00219/) (2021)
- [Interpretation of Black Box NLP Models: A Survey](https://mlsanity.com/paper/2203.17081/) (2022)
- [Stabilizing Estimates of Shapley Values with Control Variates](https://mlsanity.com/paper/2310.07672/) (2023)
- [Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillation](https://mlsanity.com/paper/2310.03112/) (2023)
- [Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations](https://mlsanity.com/paper/2311.07286/) (2023)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse](https://mlsanity.com/paper/2410.22598/) (2024)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [Rank-LIME: Local Model-Agnostic Feature Attribution for Learning to Rank](https://mlsanity.com/paper/2212.12722/) (2022)
- [Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection](https://mlsanity.com/paper/2312.12115/) (2023)
- [Statistical Significance of Feature Importance Rankings](https://mlsanity.com/paper/2401.15800/) (2024)
- [Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach](https://mlsanity.com/paper/2111.09121/) (2021)
- [Understanding Disparities in Post Hoc Machine Learning Explanation](https://mlsanity.com/paper/2401.14539/) (2024)
- [Why do explanations fail? A typology and discussion on failures in XAI](https://mlsanity.com/paper/2405.13474/) (2024)
- [Marginal Effects for Non-Linear Prediction Functions](https://mlsanity.com/paper/2201.08837/) (2022)
- [Interpretable Machine Learning for Survival Analysis](https://mlsanity.com/paper/2403.10250/) (2024)
- [Explaining Large Language Models with gSMILE](https://mlsanity.com/paper/2505.21657/) (2025)
- [Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE](https://mlsanity.com/paper/2509.03626/) (2025)
- [A Generic Approach for Reproducible Model Distillation](https://mlsanity.com/paper/2211.12631/) (2022)
- [Interpretability in Symbolic Regression: a benchmark of Explanatory Methods using the Feynman data set](https://mlsanity.com/paper/2404.05908/) (2024)
- [Towards consistency of rule-based explainer and black box model -- fusion of rule induction and XAI-based feature importance](https://mlsanity.com/paper/2407.14543/) (2024)
- [Mapping the Mind of an Instruction-based Image Editing using SMILE](https://mlsanity.com/paper/2412.16277/) (2024)
- [Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring](https://mlsanity.com/paper/2509.01409/) (2025)
- [When Stability meets Sufficiency: Informative Explanations that do not Overwhelm](https://mlsanity.com/paper/2109.06181/) (2021)

## Abstract (arXiv)

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.