Local Interpretable Model-Agnostic Explanations

Explainability Transparency

Description

LIME (Local Interpretable Model-agnostic Explanations) explains individual predictions by approximating the complex model's behaviour in a small neighbourhood around a specific instance. It works by creating perturbed versions of the input (e.g., removing words from text, changing pixel values in images, or varying feature values), obtaining the model's predictions for these variations, and training a simple interpretable model (typically linear regression) weighted by proximity to the original instance. The coefficients of this local surrogate model reveal which features most influenced the specific prediction.

Example Use Cases

Explainability

Explaining why a specific patient received a high-risk diagnosis by showing which symptoms (fever, blood pressure, age) contributed most to the prediction, helping doctors validate the AI's reasoning.

Debugging a text classifier's misclassification of a movie review by highlighting which words (e.g., sarcastic phrases) confused the model, enabling targeted model improvements.

Transparency

Providing transparent explanations to customers about automated decisions in insurance claims, showing which claim features influenced approval or denial to meet regulatory requirements.

Limitations

Explanations can be unstable due to random sampling, producing different results across multiple runs.
The linear surrogate may poorly approximate highly non-linear model behaviour in the local region.
Defining the neighbourhood size and perturbation strategy requires careful tuning for each data type.
Can be computationally expensive for explaining many instances due to repeated model queries.

Resources

marcotcr/lime

Software Package

thomasp85/lime (R package)

Software Package

Local Interpretable Model-Agnostic Explanations (lime) — lime 0.1 ...

Documentation

'Why Should I Trust You?' Explaining the Predictions of Any Classifier

Research Paper•Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin•Feb 16, 2016

How to convince your boss to trust your ML/DL models - Towards Data Science

Tutorial

Enhanced LIME — ADS 2.6.5 documentation

Documentation

Related Techniques

Name	Description	Assurance Goals
Relabelling	A preprocessing fairness technique that modifies class labels in training data to achieve equal positive outcome rates across protected groups. Also known as 'data massaging', this method identifies instances that contribute to discriminatory patterns and flips their labels (from positive to negative or vice versa) to balance the proportion of positive outcomes between demographic groups. The technique aims to remove historical bias from training data whilst preserving the overall class distribution, enabling standard classifiers to learn from discrimination-free datasets.	Fairness Transparency Reliability
Occlusion Sensitivity	Occlusion sensitivity tests which parts of the input are important by occluding (masking or removing) them and seeing how the model's prediction changes. For example, portions of an image can be covered up in a sliding window fashion; if the model's confidence drops significantly when a certain region is occluded, that region was important for the prediction.	Explainability
Coefficient Magnitudes (in Linear Models)	Coefficient Magnitudes assess feature influence in linear models by examining the absolute values of their coefficients. Features with larger absolute coefficients are considered to have a stronger impact on the prediction, while the sign of the coefficient indicates the direction of that influence (positive or negative). This technique provides a straightforward and transparent way to understand the direct linear relationship between each input feature and the model's output.	Explainability Transparency
Prediction Intervals	Prediction intervals provide a range of plausible values around a model's prediction, expressing uncertainty as 'the true value will likely fall between X and Y with Z% confidence'. For example, instead of predicting 'house price: £300,000', a prediction interval might say 'house price: £280,000 to £320,000 with 95% confidence'. This technique works by calculating upper and lower bounds that account for both model uncertainty (how confident the model is) and inherent randomness in the data. Prediction intervals are crucial for informed decision-making, as they help users understand the reliability and precision of predictions, enabling better risk assessment and planning.	Reliability Transparency Fairness
Mean Decrease Impurity	Mean Decrease Impurity (MDI) quantifies a feature's importance in tree-based models (e.g., Random Forests, Gradient Boosting Machines) by measuring the total reduction in impurity (e.g., Gini impurity, entropy) across all splits where the feature is used. Features that lead to larger, more consistent reductions in impurity are considered more important, indicating their effectiveness in creating homogeneous child nodes and improving predictive accuracy.	Explainability Reliability
Contextual Decomposition	Contextual Decomposition explains LSTM and RNN predictions by decomposing the final hidden state into contributions from individual inputs and their interactions. Unlike simpler attribution methods, it separates the direct contribution of specific words or phrases from the contextual effects of surrounding words. This is particularly useful for understanding how sequential models process language, as it can identify whether a word's influence comes from its individual meaning or from its interaction with nearby words in the sequence.	Explainability Transparency

Tags

Applicable Models:

Data Requirements:

No Special Requirements

Data Type:

Evidence Type:

Qualitative Report

Quantitative Metric

Expertise Needed:

Explanatory Scope:

Lifecycle Stage:

Model Development

System Deployment And Use

Technique Type: