Does It Make Sense to Explain a Black Box With Another Black Box?

arXiv:2404.14943v1 Announce Type: cross
Abstract: Although counterfactual explanations are a popular approach to explain ML black-box classifiers, they are less widespread in NLP. Most methods find those explanations by iteratively perturbing the target document until it is classified differently by the black box. We identify two main families of counterfactual explanation methods in the literature, namely, (a) \emph{transparent} methods that perturb the target by adding, removing, or replacing words, and (b) \emph{opaque} approaches that project the target document into a …

abstract arxiv black box box classifiers counterfactual cs.cl cs.lg document identify nlp popular sense type