Local interpretable model-agnostic explanations
Algorithms AIMech:LIME DRAFT
Aliases: LIME
A prediction-explanation method fitting an interpretable surrogate to locally weighted samples of a model's behavior.
Identity Notes & Concept Scope
LIME is a local surrogate explanation procedure, not an inherently explainable model, a guarantee of global fidelity, or the separate SP-LIME representative-selection method.
Claims & Grounded Evidence
1 Claim
Mechanism
#mechanism
Perturbed interpretable inputs are mapped back to model inputs and labeled by model outputs; fitting balances a locality-weighted fidelity loss against surrogate complexity.
⚠️ Curated Limitations & Negative Results
- The source explicitly distinguishes local fidelity from global fidelity.
- Choice of interpretable representation, neighborhood and surrogate family is part of the method's scope; explanations are not a general certification of trustworthiness.
Artificial Intelligence Ontology (AIO) Grounding
Mapped AIO Classes
| AIO Target Class | Mapping Relation | Mapping Rationale |
|---|---|---|
AIO:Model
Model
|
related_match | The method fits a local surrogate to the behavior of a predictive model. This directly supported analysis relationship does not equate the explanation method with a model or assert a model superclass. |
Evidence Sources & Primary Literature
1 Source| Source ID | Publication / Document | Type / Access | Reference & Checksum |
|---|---|---|---|
original-paper
|
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
|
primary paper
full_text
|
ID: arXiv:1602.04938v3
sha256:365079753571…
|
Curation Provenance
Curator: Codex
Method: ai_assisted
Model: GPT-6
Created: 2026-10-11T03:12:53Z
Updated: 2026-10-11T04:02:04Z
Source File:
data/curated/LIME.yaml