# Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models

arXiv: https://arxiv.org/abs/2001.11757 · HTML: https://mlsanity.com/paper/2001.11757/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2020.

## Built on by (most cited first, 30 of 40)

- [GLIME: General, Stable and Local LIME Explanation](https://mlsanity.com/paper/2311.15722/) (2023)
- [Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability](https://mlsanity.com/paper/2108.06907/) (2021)
- [Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set](https://mlsanity.com/paper/2110.13369/) (2021)
- [Developing a Fidelity Evaluation Approach for Interpretable Machine Learning](https://mlsanity.com/paper/2106.08492/) (2021)
- [Auditing Local Explanations is Hard](https://mlsanity.com/paper/2407.13281/) (2024)
- [Boundary-Aware Uncertainty for Feature Attribution Explainers](https://mlsanity.com/paper/2210.02419/) (2022)
- [The Effect of Balancing Methods on Model Behavior in Imbalanced Classification Problems](https://mlsanity.com/paper/2307.00157/) (2023)
- [Explanation Multiplicity in SHAP: Characterization and Assessment](https://mlsanity.com/paper/2601.12654/) (2026)
- [Sensing accident-prone features in urban scenes for proactive driving and accident prevention](https://mlsanity.com/paper/2202.12788/) (2022)
- [Enabling Synthetic Data adoption in regulated domains](https://mlsanity.com/paper/2204.06297/) (2022)
- [Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP](https://mlsanity.com/paper/2209.07623/) (2022)
- [Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models](https://mlsanity.com/paper/2209.11539/) (2022)
- [Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent](https://mlsanity.com/paper/2407.14486/) (2024)
- [Evaluating the stability of model explanations in instance-dependent cost-sensitive credit scoring](https://mlsanity.com/paper/2509.01409/) (2025)
- [On The Variability of Concept Activation Vectors](https://mlsanity.com/paper/2509.24058/) (2025)
- [On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2510.12201/) (2025)
- [SMACE: A New Method for the Interpretability of Composite Decision Systems](https://mlsanity.com/paper/2111.08749/) (2021)
- [Topological Representations of Local Explanations](https://mlsanity.com/paper/2201.02155/) (2022)
- [RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations](https://mlsanity.com/paper/2209.09157/) (2022)
- [Calculating and Visualizing Counterfactual Feature Importance Values](https://mlsanity.com/paper/2306.06506/) (2023)
- [TrustyAI Explainability Toolkit](https://mlsanity.com/paper/2104.12717/) (2021)
- [Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning](https://mlsanity.com/paper/2201.12143/) (2022)
- [XAI in the context of Predictive Process Monitoring: Too much to Reveal](https://mlsanity.com/paper/2202.08265/) (2022)
- [On the Bias-Variance Characteristics of LIME and SHAP in High Sparsity Movie Recommendation Explanation Tasks](https://mlsanity.com/paper/2206.04784/) (2022)
- [Measuring the Driving Forces of Predictive Performance: Application to Credit Scoring](https://mlsanity.com/paper/2212.05866/) (2022)
- [CLIMAX: An exploration of Classifier-Based Contrastive Explanations](https://mlsanity.com/paper/2307.00680/) (2023)
- [Probabilistic Prediction of Longitudinal Trajectory Considering Driving Heterogeneity with Interpretability](https://mlsanity.com/paper/2312.12123/) (2023)
- [Coherent Local Explanations for Mathematical Optimization](https://mlsanity.com/paper/2502.04840/) (2025)
- [EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs](https://mlsanity.com/paper/2512.22240/) (2025)
- [Inherent Inconsistencies of Feature Importance](https://mlsanity.com/paper/2206.08204/) (2022)

## Abstract (arXiv)

Nowadays we are witnessing a transformation of the business processes towards a more computation driven approach. The ever increasing usage of Machine Learning techniques is the clearest example of such trend. This sort of revolution is often providing advantages, such as an increase in prediction accuracy and a reduced time to obtain the results. However, these methods present a major drawback: it is very difficult to understand on what grounds the algorithm took the decision. To address this issue we consider the LIME method. We give a general background on LIME then, we focus on the stability issue: employing the method repeated times, under the same conditions, may yield to different explanations. Two complementary indices are proposed, to measure LIME stability. It is important for the practitioner to be aware of the issue, as well as to have a tool for spotting it. Stability guarantees LIME explanations to be reliable, therefore a stability assessment, made through the proposed indices, is crucial. As a case study, we apply both Machine Learning and classical statistical techniques to Credit Risk data. We test LIME on the Machine Learning algorithm and check its stability. Eventually, we examine the goodness of the explanations returned.