Abstract
Counterfactual explanations present an effective way to interpret predictions of black-box machine learning algorithms. Whereas there is a significant body of research on counterfactual reasoning in philosophy and theoretical computer science, little attention has been paid to counterfactuals in regard to their explanatory capacity. In this paper, we review methods of argumentation theory and natural language generation that counterfactual explanation generation could benefit from most and discuss prospective directions for further research on counterfactual generation in explainable Artificial Intelligence.
Highlights
Automatic decision-making systems using blackbox machine learning (ML) algorithms are widely used in various complex domains from legislation (Greenleaf et al, 2018) to health care (Gargeya and Leng, 2017)
We focus on abstract argumentation (AA) frameworks as a prospective theoretical basis for counterfactual explanation generation
Our literature review has revised the foundations of current approaches to counterfactual explanation generation
Summary
Automatic decision-making systems using blackbox machine learning (ML) algorithms are widely used in various complex domains from legislation (Greenleaf et al, 2018) to health care (Gargeya and Leng, 2017). Such systems cannot be trusted blindly as their output often comes unexplained to end users (Rudin, 2018). This work supports a discussion on prospective methods for argumentative conversational agent development.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
