How people reason with counterfactual and causal explanations for Artificial Intelligence decisions in familiar and unfamiliar domains.

ABSTRACT: Few empirical studies have examined how people understand counterfactual explanations for other people's decisions, for example, "if you had asked for a lower amount, your loan application would have been approved". Yet many current Artificial Intelligence (AI) decision support systems rely on counterfactual explanations to improve human understanding and trust. We compared counterfactual explanations to causal ones, i.e., "because you asked for a high amount, your loan application was not approved", for an AI's decisions in a familiar domain (alcohol and driving) and an unfamiliar one (chemical safety) in four experiments (n = 731). Participants were shown inputs to an AI system, its decisions, and an explanation for each decision; they attempted to predict the AI's decisions, or to make

SUBMITTER: Celar L 

PROVIDER: S-EPMC10520145 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature