Issues with post-hoc counterfactual explanations: a discussion

Understand

Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier.

• However, the assumptions they make about the data and the classifier make them unreliable in many contexts.
• In this paper, we discuss three desirable properties and approaches to quantify them: proximity, connectedness and stability.
• In addition, we illustrate that there is a risk for post-hoc counterfactual approaches to not satisfy these properties.