mlsanityData to 7 Oct 2026

Explaining the Explainer: A First Theoretical Analysis of LIME

arXiv 2001.03447 ↗First posted 10 Jan 2020cs.LG stat.MLcited by 89

Not on the map. Why?

Abstract (arXiv)

Machine learning is used more and more often for sensitive applications, sometimes replacing humans in critical decision-making processes. As such, interpretability of these algorithms is a pressing need. One popular algorithm to provide interpretability is LIME (Local Interpretable Model-Agnostic Explanation). In this paper, we provide the first theoretical analysis of LIME. We derive closed-form expressions for the coefficients of the interpretable model when the function to explain is linear. The good news is that these coefficients are proportional to the gradient of the function to explain: LIME indeed discovers meaningful features. However, our analysis also reveals that poor choices of parameters can lead LIME to miss important features.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 13; 2023: 19; 2024: 15; 2025: 13; 2026: 13.

89 papers.

Sort:

By area:

  1. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  2. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  3. 2022From Shapley Values to Generalized Additive Models and backcited by 59
  4. 2022Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contextscited by 53
  5. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  6. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  7. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  8. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  9. 2021What does LIME really see in images?cited by 21
  10. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  11. 2021Connecting Interpretability and Robustness in Decision Trees through Separationcited by 16
  12. 2021Near-Optimal Explainable k-Means for All Dimensionscited by 13
38 more
  1. 2022Unfooling Perturbation-Based Post Hoc Explainerscited by 12
  2. 2023Theoretical Behavior of XAI Methods in the Presence of Suppressor Variablescited by 12
  3. 2023Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attackcited by 10
  4. 2021Ensembles of Random SHAPscited by 8
  5. 2022s-LIME: Reconciling Locality and Fidelity in Linear Explanationscited by 8
  6. 2024Rethinking Explainable Machine Learning as Applied Statisticscited by 8
  7. 2024Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformerscited by 8
  8. 2022A Survey of Neural Treescited by 7
  9. 2023Manipulation Risks in Explainable AI: The Implications of the Disagreement Problemcited by 7
  10. 2023Explainable Fraud Detection with Deep Symbolic Classificationcited by 7
  11. 2024A Theory of Interpretable Approximationscited by 7
  12. 2021Certification of embedded systems based on Machine Learning: A surveycited by 6
  13. 2021An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Datacited by 6
  14. 2021Reducing Unintended Bias of ML Models on Tabular and Textual Datacited by 6
  15. 2021Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approachcited by 6
  16. 2022A Sea of Words: An In-Depth Analysis of Anchors for Text Datacited by 6
  17. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  18. 2023Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attributioncited by 6
  19. 2024Why do explanations fail? A typology and discussion on failures in XAIcited by 6
  20. 2022A Means-End Account of Explainable Artificial Intelligencecited by 5
  21. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
  22. 2021A Framework for Evaluating Post Hoc Feature-Additive Explainerscited by 3
  23. 2021Attention-like feature explanation for tabular datacited by 3
  24. 2022Towards a Theory of Faithfulness: Faithful Explanations of Differentiable Classifiers over Continuous Datacited by 3
  25. 2023SurvBeX: An explanation method of the machine learning survival models based on the Beran estimatorcited by 3
  26. 2024Using Stratified Sampling to Improve LIME Image Explanationscited by 3
  27. 2024Explainable Lung Disease Classification from Chest X-Ray Images Utilizing Deep Learning and XAIcited by 3
  28. 2024FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Predictioncited by 3
  29. 2024Engineering Trustworthy AI: A Developer Guide for Empirical Risk Minimizationcited by 3
  30. 2024Mapping the Mind of an Instruction-based Image Editing using SMILEcited by 3
  31. 2025Towards Explainable Fusion and Balanced Learning in Multimodal Sentiment Analysiscited by 3
  32. 2025Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the roomcited by 3
  33. 2021SMACE: A New Method for the Interpretability of Composite Decision Systemscited by 2
  34. 2023How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?cited by 2
  35. 2023Faithful and Robust Local Interpretability for Textual Predictionscited by 2
  36. 2025Justified Evidence Collection for Argument-based AI Fairness Assurancecited by 2
  37. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  38. 2025Informative Post-Hoc Explanations Only Exist for Simple Functionscited by 2

50 most cited of 89 All 89 (JSON)