# OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms

arXiv: https://arxiv.org/abs/2006.05714 · HTML: https://mlsanity.com/paper/2006.05714/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

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

- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [On Locality of Local Explanation Models](https://mlsanity.com/paper/2106.14648/) (2021)
- [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)
- [s-LIME: Reconciling Locality and Fidelity in Linear Explanations](https://mlsanity.com/paper/2208.01510/) (2022)
- [Extending Logic Explained Networks to Text Classification](https://mlsanity.com/paper/2211.09732/) (2022)
- [Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillation](https://mlsanity.com/paper/2310.03112/) (2023)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [Recent Advances in Malware Detection: Graph Learning and Explainability](https://mlsanity.com/paper/2502.10556/) (2025)
- [A novel approach to generate datasets with XAI ground truth to evaluate image models](https://mlsanity.com/paper/2302.05624/) (2023)
- [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)
- [Mapping the Mind of an Instruction-based Image Editing using SMILE](https://mlsanity.com/paper/2412.16277/) (2024)
- [Unsupervised discovery of Interpretable Visual Concepts](https://mlsanity.com/paper/2309.00018/) (2023)
- [Axiomatic Explainer Globalness via Optimal Transport](https://mlsanity.com/paper/2411.01126/) (2024)
- [Attribution Explanations for Deep Neural Networks: A Theoretical Perspective](https://mlsanity.com/paper/2508.07636/) (2025)
- [TrustyAI Explainability Toolkit](https://mlsanity.com/paper/2104.12717/) (2021)
- [Using Decision Tree as Local Interpretable Model in Autoencoder-based LIME](https://mlsanity.com/paper/2204.03321/) (2022)
- [CLIMAX: An exploration of Classifier-Based Contrastive Explanations](https://mlsanity.com/paper/2307.00680/) (2023)
- [Interpreting Outliers in Time Series Data through Decoding Autoencoder](https://mlsanity.com/paper/2409.01713/) (2024)
- [Surrogate Modeling for Explainable Predictive Time Series Corrections](https://mlsanity.com/paper/2412.19897/) (2024)
- [Regional Explanations: Bridging Local and Global Variable Importance](https://mlsanity.com/paper/2604.11223/) (2026)
- [ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI](https://mlsanity.com/paper/2607.09649/) (2026)
- [Balancing Explainability-Accuracy of Complex Models](https://mlsanity.com/paper/2305.14098/) (2023)
- ["Honey, Tell Me What's Wrong", Global Explanation of Textual Discriminative Models through Cooperative Generation](https://mlsanity.com/paper/2310.18063/) (2023)
- [Privacy-Preserving Model and Preprocessing Verification for Machine Learning](https://mlsanity.com/paper/2501.08236/) (2025)
- [Green LIME: Improving AI Explainability through Design of Experiments](https://mlsanity.com/paper/2502.12753/) (2025)
- [MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Study](https://mlsanity.com/paper/2503.20758/) (2025)
- [LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text](https://mlsanity.com/paper/2601.11746/) (2026)
- [Enhancing LIME using Neural Decision Trees](https://mlsanity.com/paper/2603.20919/) (2026)

## Abstract (arXiv)

Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the prediction. The model is trained on randomly generated data points, sampled from the training dataset distribution and weighted according to the distance from the reference point - the one being explained by LIME. Feature selection is applied to keep only the most important variables. LIME is widespread across different domains, although its instability - a single prediction may obtain different explanations - is one of the major shortcomings. This is due to the randomness in the sampling step, as well as to the flexibility in tuning the weights and determines a lack of reliability in the retrieved explanations, making LIME adoption problematic. In Medicine especially, clinical professionals trust is mandatory to determine the acceptance of an explainable algorithm, considering the importance of the decisions at stake and the related legal issues. In this paper, we highlight a trade-off between explanation's stability and adherence, namely how much it resembles the ML model. Exploiting our innovative discovery, we propose a framework to maximise stability, while retaining a predefined level of adherence. OptiLIME provides freedom to choose the best adherence-stability trade-off level and more importantly, it clearly highlights the mathematical properties of the retrieved explanation. As a result, the practitioner is provided with tools to decide whether the explanation is reliable, according to the problem at hand. We extensively test OptiLIME on a toy dataset - to present visually the geometrical findings - and a medical dataset. In the latter, we show how the method comes up with meaningful explanations both from a medical and mathematical standpoint.