# GLIME: General, Stable and Local LIME Explanation

arXiv: https://arxiv.org/abs/2311.15722 · HTML: https://mlsanity.com/paper/2311.15722/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [An Introduction to Matrix Concentration Inequalities](https://mlsanity.com/paper/1501.01571/) (2015)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations](https://mlsanity.com/paper/2206.01254/) (2022)
- [DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems](https://mlsanity.com/paper/1906.10263/) (2019)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [Interpretable Credit Application Predictions With Counterfactual Explanations](https://mlsanity.com/paper/1811.05245/) (2018)
- [ALIME: Autoencoder Based Approach for Local Interpretability](https://mlsanity.com/paper/1909.02437/) (2019)
- [Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models](https://mlsanity.com/paper/2001.11757/) (2020)
- [Missingness Bias in Model Debugging](https://mlsanity.com/paper/2204.08945/) (2022)
- [Defining Locality for Surrogates in Post-hoc Interpretablity](https://mlsanity.com/paper/1806.07498/) (2018)
- [OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms](https://mlsanity.com/paper/2006.05714/) (2020)
- [What does LIME really see in images?](https://mlsanity.com/paper/2102.06307/) (2021)
- [Looking Deeper into Tabular LIME](https://mlsanity.com/paper/2008.11092/) (2020)
- [Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures](https://mlsanity.com/paper/1910.13398/) (2019)
- [A study of data and label shift in the LIME framework](https://mlsanity.com/paper/1910.14421/) (2019)
- [A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanation](https://mlsanity.com/paper/2002.07434/) (2020)

## Built on by (most cited first, 21 of 21)

- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [Attribution Explanations for Deep Neural Networks: A Theoretical Perspective](https://mlsanity.com/paper/2508.07636/) (2025)
- [Explaining the Unexplained: Revealing Hidden Correlations for Better Interpretability](https://mlsanity.com/paper/2412.01365/) (2024)
- [Minimizing False-Positive Attributions in Explanations of Non-Linear Models](https://mlsanity.com/paper/2505.11210/) (2025)
- [ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI](https://mlsanity.com/paper/2607.09649/) (2026)
- [Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems](https://mlsanity.com/paper/2412.20201/) (2024)
- [ColonScopeX: Leveraging Explainable Expert Systems with Multimodal Data for Improved Early Diagnosis of Colorectal Cancer](https://mlsanity.com/paper/2504.08824/) (2025)
- [LAMP: Extracting Local Decision Surfaces From Large Language Models](https://mlsanity.com/paper/2505.11772/) (2025)
- [ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings](https://mlsanity.com/paper/2508.13672/) (2025)
- [ABLE: Using Adversarial Pairs to Construct Local Models for Explaining Model Predictions](https://mlsanity.com/paper/2511.21952/) (2025)
- [Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models](https://mlsanity.com/paper/2512.05556/) (2025)
- [On the Definition and Detection of Cherry-Picking in Counterfactual Explanations](https://mlsanity.com/paper/2601.04977/) (2026)
- [LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text](https://mlsanity.com/paper/2601.11746/) (2026)
- [ECSEL: Explainable Classification via Signomial Equation Learning](https://mlsanity.com/paper/2601.21789/) (2026)
- [Quantifying Retriever-Generator Alignment in RAG with Local Explanations](https://mlsanity.com/paper/2601.21803/) (2026)
- [Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection](https://mlsanity.com/paper/2602.04607/) (2026)
- [Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations](https://mlsanity.com/paper/2603.14894/) (2026)
- [Enhancing LIME using Neural Decision Trees](https://mlsanity.com/paper/2603.20919/) (2026)
- [BREAD: Baseline-Referenced Explanations for Anomaly Diagnosis](https://mlsanity.com/paper/2608.10587/) (2026)

## Abstract (arXiv)

As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanations (LIME) [22] is a widely adpoted method for understanding model behaviors, it is unstable with respect to random seeds [35,24,3] and exhibits low local fidelity (i.e., how well the explanation approximates the model's local behaviors) [21,16]. Our study shows that this instability problem stems from small sample weights, leading to the dominance of regularization and slow convergence. Additionally, LIME's sampling neighborhood is non-local and biased towards the reference, resulting in poor local fidelity and sensitivity to reference choice. To tackle these challenges, we introduce GLIME, an enhanced framework extending LIME and unifying several prior methods. Within the GLIME framework, we derive an equivalent formulation of LIME that achieves significantly faster convergence and improved stability. By employing a local and unbiased sampling distribution, GLIME generates explanations with higher local fidelity compared to LIME. GLIME explanations are independent of reference choice. Moreover, GLIME offers users the flexibility to choose a sampling distribution based on their specific scenarios.