Explainability

Perturbation Based

Modifies inputs to measure impact on outputs (e.g., SHAP, Permutation Importance)

10 techniques in this subcategory

10 techniques
GoalsModelsData TypesDescription
SHapley Additive exPlanations
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
SHAP explains model predictions by quantifying how much each input feature contributes to the outcome. It assigns an...
Permutation Importance
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
Permutation Importance quantifies a feature's contribution to a model's performance by randomly shuffling its values and...
Sobol Indices
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
Sobol Indices quantify how much each input feature contributes to the total variance in a model's predictions through...
Local Interpretable Model-Agnostic Explanations
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
LIME (Local Interpretable Model-agnostic Explanations) explains individual predictions by approximating the complex...
Partial Dependence Plots
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
Partial Dependence Plots show how changing one or two features affects a model's predictions on average. The technique...
Occlusion Sensitivity
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Image
Occlusion sensitivity tests which parts of the input are important by occluding (masking or removing) them and seeing...
Contrastive Explanation Method
Algorithmic
Architecture/neural Networks
Paradigm/discriminative
+4
Any
The Contrastive Explanation Method (CEM) explains model decisions by generating contrastive examples that reveal what...
Out-of-Distribution Detector for Neural Networks
Algorithmic
Architecture/neural Networks
Paradigm/discriminative
+3
Any
ODIN (Out-of-Distribution Detector for Neural Networks) identifies when a neural network encounters inputs significantly...
Permutation Tests
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
Permutation tests assess the statistical significance of observed results (such as model accuracy, feature importance,...
Prompt Sensitivity Analysis
Experimental
Architecture/neural Networks/transformer/llm
Paradigm/generative
+1
Text
Prompt Sensitivity Analysis systematically evaluates how variations in input prompts affect large language model...
Rows per page
Page 1 of 1