mlsanityData to 7 Oct 2026

Which LIME should I trust? Concepts, Challenges, and Solutions

arXiv 2503.24365 ↗First posted 31 Mar 2025cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

As neural networks become dominant in essential systems, Explainable Artificial Intelligence (XAI) plays a crucial role in fostering trust and detecting potential misbehavior of opaque models. LIME (Local Interpretable Model-agnostic Explanations) is among the most prominent model-agnostic approaches, generating explanations by approximating the behavior of black-box models around specific instances. Despite its popularity, LIME faces challenges related to fidelity, stability, and applicability to domain-specific problems. Numerous adaptations and enhancements have been proposed to address these issues, but the growing number of developments can be overwhelming, complicating efforts to navigate LIME-related research. To the best of our knowledge, this is the first survey to comprehensively explore and collect LIME's foundational concepts and known limitations. We categorize and compare its various enhancements, offering a structured taxonomy based on intermediate steps and key issues. Our analysis provides a holistic overview of advancements in LIME, guiding future research and helping practitioners identify suitable approaches. Additionally, we provide a continuously updated interactive website (https://patrick-knab.github.io/which-lime-to-trust/), offering a concise and accessible overview of the survey.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 50 of its 107 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

50 of 107 references.

References · 50

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  4. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  5. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  6. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  7. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  8. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  9. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  10. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Gamecited by 148
  11. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  12. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
38 more
  1. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  2. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  3. 2021Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Surveycited by 71
  4. 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 69
  5. 2019DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systemscited by 59
  6. 2021S-LIME: Stabilized-LIME for Model Explanationcited by 52
  7. 2020BayLIME: Bayesian Local Interpretable Model-Agnostic Explanationscited by 51
  8. 2019ALIME: Autoencoder Based Approach for Local Interpretabilitycited by 41
  9. 2023Explain Any Concept: Segment Anything Meets Concept-Based Explanationcited by 37
  10. 2020SurvLIME: A method for explaining machine learning survival modelscited by 34
  11. 2022DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanationscited by 34
  12. 2018Defining Locality for Surrogates in Post-hoc Interpretablitycited by 33
  13. 2019Grid Saliency for Context Explanations of Semantic Segmentationcited by 32
  14. 2019Global Aggregations of Local Explanations for Black Box modelscited by 30
  15. 2020OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithmscited by 30
  16. 2021TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Modelscited by 28
  17. 2020An Analysis of LIME for Text Datacited by 25
  18. 2019Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Alephcited by 23
  19. 2020audioLIME: Listenable Explanations Using Source Separationcited by 22
  20. 2023Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Researchcited by 22
  21. 2020Why model why? Assessing the strengths and limitations of LIMEcited by 21
  22. 2022OmniXAI: A Library for Explainable AIcited by 21
  23. 2023GLIME: General, Stable and Local LIME Explanationcited by 21
  24. 2020Looking Deeper into Tabular LIMEcited by 20
  25. 2018Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP)cited by 19
  26. 2019bLIMEy: Surrogate Prediction Explanations Beyond LIMEcited by 17
  27. 2019NormLime: A New Feature Importance Metric for Explaining Deep Neural Networkscited by 16
  28. 2020A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanationcited by 13
  29. 2021Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainabilitycited by 12
  30. 2016A Tutorial on Regularized Partial Correlation Networkscited by 11
  31. 2024BEExAI: Benchmark to Evaluate Explainable AIcited by 11
  32. 2022Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutionscited by 10
  33. 2020MeLIME: Meaningful Local Explanation for Machine Learning Modelscited by 9
  34. 2022Explainable Artificial Intelligence (XAI) for Internet of Things: A Surveycited by 8
  35. 2022s-LIME: Reconciling Locality and Fidelity in Linear Explanationscited by 8
  36. 2020SurvLIME-Inf: A simplified modification of SurvLIME for explanation of machine learning survival modelscited by 7
  37. 2021GLIME: A new graphical methodology for interpretable model-agnostic explanationscited by 1
  38. 2024Interpreting Outliers in Time Series Data through Decoding Autoencodercited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 58
  2. 2025Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Explorationcited by 6
  3. 2025Explaining Large Language Models with gSMILEcited by 4
  4. 2026Enhancing LIME using Neural Decision Treescited by 0
  5. 2026ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AIcited by 0
  6. 2026BREAD: Baseline-Referenced Explanations for Anomaly Diagnosiscited by 0
  7. 2026When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanationscited by 0