# s-LIME: Reconciling Locality and Fidelity in Linear Explanations

arXiv: https://arxiv.org/abs/2208.01510 · HTML: https://mlsanity.com/paper/2208.01510/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 2 Aug 2022.

## Builds on (most cited first, 12 of 12)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Explaining the Explainer: A First Theoretical Analysis of LIME](https://mlsanity.com/paper/2001.03447/) (2020)
- [DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems](https://mlsanity.com/paper/1906.10263/) (2019)
- [ALIME: Autoencoder Based Approach for Local Interpretability](https://mlsanity.com/paper/1909.02437/) (2019)
- [OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms](https://mlsanity.com/paper/2006.05714/) (2020)
- [To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods](https://mlsanity.com/paper/2106.00461/) (2021)
- [The Bouncer Problem: Challenges to Remote Explainability](https://mlsanity.com/paper/1910.01432/) (2019)

## Built on by (most cited first, 8 of 8)

- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection](https://mlsanity.com/paper/2312.12115/) (2023)
- [SurvBeX: An explanation method of the machine learning survival models based on the Beran estimator](https://mlsanity.com/paper/2308.03730/) (2023)
- [Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Data](https://mlsanity.com/paper/2410.12803/) (2024)
- [Axiomatic Explainer Globalness via Optimal Transport](https://mlsanity.com/paper/2411.01126/) (2024)
- [Local Universal Explainer (LUX) -- a rule-based explainer with factual, counterfactual and visual explanations](https://mlsanity.com/paper/2310.14894/) (2023)
- ["Honey, Tell Me What's Wrong", Global Explanation of Textual Discriminative Models through Cooperative Generation](https://mlsanity.com/paper/2310.18063/) (2023)
- [SurvBeNIM: The Beran-Based Neural Importance Model for Explaining the Survival Models](https://mlsanity.com/paper/2312.06638/) (2023)

## Abstract (arXiv)

The benefit of locality is one of the major premises of LIME, one of the most prominent methods to explain black-box machine learning models. This emphasis relies on the postulate that the more locally we look at the vicinity of an instance, the simpler the black-box model becomes, and the more accurately we can mimic it with a linear surrogate. As logical as this seems, our findings suggest that, with the current design of LIME, the surrogate model may degenerate when the explanation is too local, namely, when the bandwidth parameter σ tends to zero. Based on this observation, the contribution of this paper is twofold. Firstly, we study the impact of both the bandwidth and the training vicinity on the fidelity and semantics of LIME explanations. Secondly, and based on our findings, we propose slime, an extension of LIME that reconciles fidelity and locality.