On the Interdependence of Reliance Behavior and Accuracy in AI-Assisted Decision-Making

In AI-assisted decision-making, a central promise of putting human in the loop is that they should be able to complement AI system by adhering its correct and overriding mistaken recommendations. practice, however, we often see humans tend over- or under-rely on recommendations, meaning either adhere wrong override Such reliance behavior detrimental decision-making accuracy. this work, articulate analyze interdependence between accuracy which has been largely neglected prior work. We also propose visual framework make more tangible. This helps us interpret compare empirical findings, as well obtain nuanced understanding effects interventions (e.g., explanations) decision-making. Finally, infer several interesting properties from framework: (i) when there may no possibility for them terms accuracy; (ii) cannot discern such improvement can expected either; (iii) lead an increase solely driven humans’ adherence without any ability wrong. Our work emphasizes importance measuring reporting both empirically assessing interventions.