Contextual Local Explanation for Black Box Classifiers
This provides interpretable explanations for black box classifiers, which is an incremental improvement in the field of explainable AI.
The authors tackled the problem of explaining black box classifier predictions by introducing CLE, a model-agnostic technique that approximates models locally with interpretable models, demonstrating flexibility across text, tabular, and image data and fidelity through simulated user experiments.
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an interpretable model. We demonstrate the flexibility of CLE by explaining different models for text, tabular and image classification, and the fidelity of it by doing simulated user experiments.