Explainability

Fidelity

Accurately represents true model behaviour

22 techniques in this subcategory

22 techniques
GoalsModelsData TypesDescription
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...
Coefficient Magnitudes (in Linear Models)
Metric
Architecture/linear Models
Paradigm/parametric
+2
Tabular
Coefficient Magnitudes assess feature influence in linear models by examining the absolute values of their coefficients....
Layer-wise Relevance Propagation
Algorithmic
Architecture/neural Networks
Paradigm/parametric
+2
Any
Layer-wise Relevance Propagation (LRP) explains neural network predictions by working backwards through the network to...
Contextual Decomposition
Algorithmic
Architecture/neural Networks/recurrent
Requirements/white Box
+1
Text
Contextual Decomposition explains LSTM and RNN predictions by decomposing the final hidden state into contributions from...
Taylor Decomposition
Algorithmic
Architecture/neural Networks
Requirements/gradient Access
+2
Any
Taylor Decomposition is a mathematical technique that explains neural network predictions by computing first-order and...
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...
Ridge Regression Surrogates
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
This technique approximates a complex model by training a ridge regression (a linear model with L2 regularisation) on...
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...
Individual Conditional Expectation Plots
Visualization
Architecture/model Agnostic
Requirements/black Box
Any
Individual Conditional Expectation (ICE) plots display the predicted output for individual instances as a function of a...
Classical Attention Analysis in Neural Networks
Algorithmic
Architecture/neural Networks/recurrent
Requirements/architecture Specific
+1
Any
Classical attention mechanisms in RNNs and CNNs create alignment matrices and temporal attention patterns that show how...
UMAP
Visualization
Architecture/model Agnostic
Requirements/black Box
Any
UMAP (Uniform Manifold Approximation and Projection) is a non-linear dimensionality reduction technique that creates 2D...
Influence Functions
Algorithmic
Architecture/linear Models
Architecture/neural Networks
+6
Any
Influence functions quantify how much each training example influenced a model's predictions by computing the change in...
ANCHOR
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
ANCHOR generates high-precision if-then rules that explain individual predictions by identifying the minimal set of...
RuleFit
Algorithmic
Architecture/model Agnostic
Paradigm/supervised
+1
Any
RuleFit creates interpretable surrogate models that can explain complex black-box models or serve as interpretable...
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,...
Model Distillation
Algorithmic
Architecture/neural Networks
Paradigm/parametric
+3
Any
Model distillation transfers knowledge from a large, complex model (teacher) to a smaller, more efficient model...
Generalized Additive Models
Algorithmic
Architecture/linear Models/gam
Paradigm/parametric
+2
Tabular
An intrinsically interpretable modelling technique that extends linear models by allowing flexible, nonlinear...
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...
Causal Mediation Analysis in Language Models
Mechanistic Interpretability
Architecture/neural Networks/transformer
Architecture/neural Networks/transformer/llm
+3
Text
Causal mediation analysis in language models is a mechanistic interpretability technique that systematically...
Rows per page
Page 1 of 2