Erica Fung

Abstract: While it is well-known that AI systems might bring about unfair social impacts by influencing social schemas, much attention has been paid to instances where the content presented by AI systems explicitly demeans marginalized groups or reinforces problematic stereotypes. This paper urges critical scrutiny to be paid to instances that shape social schemas through subtler manners. Drawing from […]

Abstract: Making AI explainable has become an increasingly urgent demand, and one of the popular approaches is to generate so-called counterfactual explanations. In this talk, I attempt a philosophical critique of the key aspects of this approach, and raise an important challenge arising from a tension between two constraints on a good counterfactual explanation in