---
title: "LIME"
description: "Local Interpretable Model-agnostic Explanations: explains one prediction by fitting a simple interpretable model to the black box's behaviour on perturbed samples around the input; vulnerable to…"
canonical: https://aigovernanceengineer.com/glossary/lime
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-24
---

# LIME

Local Interpretable Model-agnostic Explanations: explains one prediction by fitting a simple interpretable model to the black box's behaviour on perturbed samples around the input [1]; vulnerable to off-manifold manipulation.

- Developed in: [ch. 16, Feature attribution: SHAP, LIME and integrated gradients](https://aigovernanceengineer.com/bok/fairness-and-explainability#feature-attribution-shap-lime-and-integrated-gradients)
- Chapters: [ch. 16, Fairness & XAI](https://aigovernanceengineer.com/bok/fairness-and-explainability)
- Contrast with: [SHAP](https://aigovernanceengineer.com/glossary/shap)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-lime

## Sources

[1] "'Why Should I Trust You?': Explaining the Predictions of Any Classifier" (Ribeiro, Singh and Guestrin; LIME; arXiv 1602.04938). arXiv. 2016-02-16. https://arxiv.org/abs/1602.04938 (verified: primary)