Declarative Approaches to Counterfactual Explanations for Classification
This work provides a declarative method for explainable AI, offering incremental improvements in generating causality-based explanations for classification tasks.
The authors tackled the problem of generating counterfactual explanations for classification models by proposing answer-set programs to compute interventions that maximize responsibility scores for feature values, enabling explanations with black-box or logic-based models.
We propose answer-set programs that specify and compute counterfactual interventions on entities that are input on a classification model. In relation to the outcome of the model, the resulting counterfactual entities serve as a basis for the definition and computation of causality-based explanation scores for the feature values in the entity under classification, namely "responsibility scores". The approach and the programs can be applied with black-box models, and also with models that can be specified as logic programs, such as rule-based classifiers. The main focus of this work is on the specification and computation of "best" counterfactual entities, i.e. those that lead to maximum responsibility scores. From them one can read off the explanations as maximum responsibility feature values in the original entity. We also extend the programs to bring into the picture semantic or domain knowledge. We show how the approach could be extended by means of probabilistic methods, and how the underlying probability distributions could be modified through the use of constraints. Several examples of programs written in the syntax of the DLV ASP-solver, and run with it, are shown.