HAI Weekly Seminar with Kate Vredenburgh: Against Rationale Explanations

Timezone is in PST.

Kate Vredenburgh’s work is mainly in political philosophy, the philosophy of (social) science, and the ethics of technology; on topics that intersect with ethics, epistemology, and metaphysics.

ABSTRACT: In this talk, I will argue against one popular socio-technical solution to the problem of opacity: rationale explanations. Such explanations are taken to achieve many important political values enabled by explanations, such as trust, recourse, respect, and accountability, as well as to enable decision-makers to comply with GDPR. For example, by providing data subjects with a single or small set of counterfactuals that link specific inputs to a desired output value, rationale explanations based on counterfactuals enable individuals to achieve recourse. However, I argue that rationale explanations are often not the best means to enable the relevant political values. The general insight is that rationale based explanations combine two different types of politically important explanations: causal explanations, that give individuals the information needed to adjust their behavior, and normative explanations, which justify the use of the system or a particular application of it.

How to Attend

Registration is requested. Use the Sign Up link below.

Organized By: The Stanford Institute for Human-Centered Artificial Intelligence