# A study of data and label shift in the LIME framework

arXiv: https://arxiv.org/abs/1910.14421 · HTML: https://mlsanity.com/paper/1910.14421/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 17 of 17)

- [GLIME: General, Stable and Local LIME Explanation](https://mlsanity.com/paper/2311.15722/) (2023)
- [Calibrated Explanations: with Uncertainty Information and Counterfactuals](https://mlsanity.com/paper/2305.02305/) (2023)
- [Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions](https://mlsanity.com/paper/2209.15409/) (2022)
- [DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction](https://mlsanity.com/paper/2303.01576/) (2023)
- [Interpretable Survival Analysis for Heart Failure Risk Prediction](https://mlsanity.com/paper/2310.15472/) (2023)
- [Calibrated Explanations for Regression](https://mlsanity.com/paper/2308.16245/) (2023)
- [The Blame Problem in Evaluating Local Explanations, and How to Tackle it](https://mlsanity.com/paper/2310.03466/) (2023)
- [LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations](https://mlsanity.com/paper/2111.08094/) (2021)
- [Data augmentation and explainability for bias discovery and mitigation in deep learning](https://mlsanity.com/paper/2308.09464/) (2023)
- [Interpretable Prediction and Feature Selection for Survival Analysis](https://mlsanity.com/paper/2404.14689/) (2024)
- [Transparent Networks for Multivariate Time Series](https://mlsanity.com/paper/2410.10535/) (2024)
- [ComplAI: Theory of A Unified Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models](https://mlsanity.com/paper/2212.14599/) (2022)
- [Ensemble Interpretation: A Unified Method for Interpretable Machine Learning](https://mlsanity.com/paper/2312.06255/) (2023)
- [Evaluating Local Explanations using White-box Models](https://mlsanity.com/paper/2106.02488/) (2021)
- [Robustness and Usefulness in AI Explanation Methods](https://mlsanity.com/paper/2203.03729/) (2022)
- [Evaluating the overall sensitivity of saliency-based explanation methods](https://mlsanity.com/paper/2306.13682/) (2023)
- [MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Study](https://mlsanity.com/paper/2503.20758/) (2025)

## Abstract (arXiv)

LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero features of the predicted instance. After that, the perturbed instances are fed into the black-box model to obtain labels for these, which are then used for training the interpretable model. In this study, we present a systematic evaluation of the interpretable models that are output by LIME on the two use-cases that were considered in the original paper introducing the approach; text classification and object detection. The investigation shows that the perturbation and labeling phases result in both data and label shift. In addition, we study the correlation between the shift and the fidelity of the interpretable model and show that in certain cases the shift negatively correlates with the fidelity. Based on these findings, it is argued that there is a need for a new sampling approach that mitigates the shift in the LIME's framework.