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

TLDR

Machine learning models are widely used yet largely black boxes, and understanding their predictions is essential for assessing trust, guiding deployment decisions, and improving model reliability. The authors introduce LIME, an explanation technique that locally learns an interpretable model around a prediction, and a submodular optimization method to present representative, non‑redundant explanations. The methods are applied to diverse models, including random forests for text and neural networks for images, demonstrating their flexibility. Experiments with simulated data and human subjects demonstrate that explanations help users decide whether to trust predictions, choose between models, improve untrustworthy classifiers, and identify reasons for distrust.

Abstract

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.