mlsanityData to 7 Oct 2026

OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms

arXiv 2006.05714 ↗First posted 10 Jun 2020cs.LG cs.AI stat.MLcited by 30

Not on the map. Why?

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.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 7; 2024: 4; 2025: 8; 2026: 4.

30 papers.

Sort:

By area:

  1. 2021S-LIME: Stabilized-LIME for Model Explanationcited by 52
  2. 2021On Locality of Local Explanation Modelscited by 25
  3. 2023GLIME: General, Stable and Local LIME Explanationcited by 21
  4. 2021Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainabilitycited by 12
  5. 2022s-LIME: Reconciling Locality and Fidelity in Linear Explanationscited by 8
  6. 2022Extending Logic Explained Networks to Text Classificationcited by 8
  7. 2023Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillationcited by 8
  8. 2025Which LIME should I trust? Concepts, Challenges, and Solutionscited by 7
  9. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  10. 2023A novel approach to generate datasets with XAI ground truth to evaluate image modelscited by 4
  11. 2025Explaining Large Language Models with gSMILEcited by 4
  12. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
18 more
  1. 2024Mapping the Mind of an Instruction-based Image Editing using SMILEcited by 3
  2. 2023Unsupervised discovery of Interpretable Visual Conceptscited by 2
  3. 2024Axiomatic Explainer Globalness via Optimal Transportcited by 2
  4. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  5. 2021TrustyAI Explainability Toolkitcited by 1
  6. 2022Using Decision Tree as Local Interpretable Model in Autoencoder-based LIMEcited by 1
  7. 2023CLIMAX: An exploration of Classifier-Based Contrastive Explanationscited by 1
  8. 2024Interpreting Outliers in Time Series Data through Decoding Autoencodercited by 1
  9. 2024Surrogate Modeling for Explainable Predictive Time Series Correctionscited by 1
  10. 2023Balancing Explainability-Accuracy of Complex Modelscited by 0
  11. 2023"Honey, Tell Me What's Wrong", Global Explanation of Textual Discriminative Models through Cooperative Generationcited by 0
  12. 2025Privacy-Preserving Model and Preprocessing Verification for Machine Learningcited by 0
  13. 2025Green LIME: Improving AI Explainability through Design of Experimentscited by 0
  14. 2025MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Studycited by 0
  15. 2026LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Textcited by 0
  16. 2026Enhancing LIME using Neural Decision Treescited by 0
  17. 2026Regional Explanations: Bridging Local and Global Variable Importancecited by 0
  18. 2026ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AIcited by 0