# An Analysis of LIME for Text Data

arXiv: https://arxiv.org/abs/2010.12487 · HTML: https://mlsanity.com/paper/2010.12487/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 25 of 25)

- [Missingness Bias in Model Debugging](https://mlsanity.com/paper/2204.08945/) (2022)
- [Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making](https://mlsanity.com/paper/2209.11812/) (2022)
- [What does LIME really see in images?](https://mlsanity.com/paper/2102.06307/) (2021)
- [Connecting Interpretability and Robustness in Decision Trees through Separation](https://mlsanity.com/paper/2102.07048/) (2021)
- [Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models](https://mlsanity.com/paper/2504.00573/) (2025)
- [Attention Meets Post-hoc Interpretability: A Mathematical Perspective](https://mlsanity.com/paper/2402.03485/) (2024)
- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack](https://mlsanity.com/paper/2305.12351/) (2023)
- [Natural Language Processing RELIES on Linguistics](https://mlsanity.com/paper/2405.05966/) (2024)
- [Towards Improved Input Masking for Convolutional Neural Networks](https://mlsanity.com/paper/2211.14646/) (2022)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [A Sea of Words: An In-Depth Analysis of Anchors for Text Data](https://mlsanity.com/paper/2205.13789/) (2022)
- [Using Stratified Sampling to Improve LIME Image Explanations](https://mlsanity.com/paper/2403.17742/) (2024)
- [Faithful and Robust Local Interpretability for Textual Predictions](https://mlsanity.com/paper/2311.01605/) (2023)
- [Attribution Explanations for Deep Neural Networks: A Theoretical Perspective](https://mlsanity.com/paper/2508.07636/) (2025)
- [Comparing Feature Importance and Rule Extraction for Interpretability on Text Data](https://mlsanity.com/paper/2207.01420/) (2022)
- [Understanding Post-hoc Explainers: The Case of Anchors](https://mlsanity.com/paper/2303.08806/) (2023)
- [The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI](https://mlsanity.com/paper/2406.15839/) (2024)
- [Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI](https://mlsanity.com/paper/2501.02042/) (2025)
- [A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detection](https://mlsanity.com/paper/2503.11838/) (2025)
- [Interpretability of Fine-grained Classification of Sadness and Depression](https://mlsanity.com/paper/2203.10432/) (2022)
- [PE: A Poincare Explanation Method for Fast Text Hierarchy Generation](https://mlsanity.com/paper/2403.16554/) (2024)
- [Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study](https://mlsanity.com/paper/2508.09776/) (2025)
- [Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations](https://mlsanity.com/paper/2607.15482/) (2026)
- [When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations](https://mlsanity.com/paper/2609.07462/) (2026)

## 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.