mlsanityData to 7 Oct 2026

An Analysis of LIME for Text Data

arXiv 2010.12487 ↗First posted 23 Oct 2020stat.ML cs.CL cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Text data are increasingly handled in an automated fashion by machine learning algorithms. But the models handling these data are not always well-understood due to their complexity and are more and more often referred to as "black-boxes." Interpretability methods aim to explain how these models operate. Among them, LIME has become one of the most popular in recent years. However, it comes without theoretical guarantees: even for simple models, we are not sure that LIME behaves accurately. In this paper, we provide a first theoretical analysis of LIME for text data. As a consequence of our theoretical findings, we show that LIME indeed provides meaningful explanations for simple models, namely decision trees and linear models.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 3; 2024: 6; 2025: 6; 2026: 2.

25 papers.

Sort:

By area:

  1. 2022Missingness Bias in Model Debuggingcited by 36
  2. 2022Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Makingcited by 25
  3. 2021What does LIME really see in images?cited by 21
  4. 2021Connecting Interpretability and Robustness in Decision Trees through Separationcited by 16
  5. 2025Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Modelscited by 13
  6. 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspectivecited by 11
  7. 2024Multi-Level Explanations for Generative Language Modelscited by 11
  8. 2023Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attackcited by 10
  9. 2024Natural Language Processing RELIES on Linguisticscited by 9
  10. 2022Towards Improved Input Masking for Convolutional Neural Networkscited by 7
  11. 2025Which LIME should I trust? Concepts, Challenges, and Solutionscited by 7
  12. 2022A Sea of Words: An In-Depth Analysis of Anchors for Text Datacited by 6
13 more
  1. 2024Using Stratified Sampling to Improve LIME Image Explanationscited by 3
  2. 2023Faithful and Robust Local Interpretability for Textual Predictionscited by 2
  3. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  4. 2022Comparing Feature Importance and Rule Extraction for Interpretability on Text Datacited by 1
  5. 2023Understanding Post-hoc Explainers: The Case of Anchorscited by 1
  6. 2024The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AIcited by 1
  7. 2025Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AIcited by 1
  8. 2025A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detectioncited by 1
  9. 2022Interpretability of Fine-grained Classification of Sadness and Depressioncited by 0
  10. 2024PE: A Poincare Explanation Method for Fast Text Hierarchy Generationcited by 0
  11. 2025Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Studycited by 0
  12. 2026Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbationscited by 0
  13. 2026When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanationscited by 0