Post-hoc techniques represent a vast collection of methods created to specifically address the black-box problem, where we do not have access to the internal feature representations or model structure. There are considerable advantages to using post-hoc methods. They can work for a wide variety of model algorithms. They allow for different representations to be used for internal modeling and explanation. They can also provide different types of explanations for the same model. However, there is a trade-off between the fidelity and comprehensibility of explanations.
