Learning to Advise Humans in High-Stakes Settings
This addresses the challenge of optimizing AI-human team performance in critical decision-making scenarios, though it is incremental as it builds on existing AI-assisted decision-making concepts.
The paper tackles the problem of AI systems advising expert decision-makers in high-stakes settings by developing a framework that accounts for human reconciliation costs and imperfect discretion behavior, resulting in TeamRules, which robustly improves team decision accuracy across synthetic and real-world benchmarks.
Expert decision-makers (DMs) in high-stakes AI-assisted decision-making (AIaDM) settings receive and reconcile recommendations from AI systems before making their final decisions. We identify distinct properties of these settings which are key to developing AIaDM models that effectively benefit team performance. First, DMs incur reconciliation costs from exerting decision-making resources (e.g., time and effort) when reconciling AI recommendations that contradict their own judgment. Second, DMs in AIaDM settings exhibit algorithm discretion behavior (ADB), i.e., an idiosyncratic tendency to imperfectly accept or reject algorithmic recommendations for any given decision task. The human's reconciliation costs and imperfect discretion behavior introduce the need to develop AI systems which (1) provide recommendations selectively, (2) leverage the human partner's ADB to maximize the team's decision accuracy while regularizing for reconciliation costs, and (3) are inherently interpretable. We refer to the task of developing AI to advise humans in AIaDM settings as learning to advise and we address this task by first introducing the AI-assisted Team (AIaT)-Learning Framework. We instantiate our framework to develop TeamRules (TR): an algorithm that produces rule-based models and recommendations for AIaDM settings. TR is optimized to selectively advise a human and to trade-off reconciliation costs and team accuracy for a given environment by leveraging the human partner's ADB. Evaluations on synthetic and real-world benchmark datasets with a variety of simulated human accuracy and discretion behaviors show that TR robustly improves the team's objective across settings over interpretable, rule-based alternatives.