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.
Human-AI collectives produce the most accurate differential diagnoses
Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所);The Human Diagnosis Project(人类诊断项目);University of Cologne(科隆大学);Harvey Mudd College(哈维穆德学院);Oxford University(牛津大学);Kaiser Permanente(凯撒永久医疗);ISTC-CNR(意大利国家研究委员会认知科学与技术研究所);Technical University Berlin(柏林工业大学)
Understanding Data Usage when Making High-Stakes Frontline Decisions in Homelessness Services
Computer Science, University of Calgary(卡尔加里大学计算机科学);Electrical and Software Engineering, University of Calgary(卡尔加里大学电气与软件工程系);Information Science, University of Colorado Boulder(科罗拉多大学博尔德分校信息科学);Social Work, University of Calgary(卡尔加里大学社会工作)
Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains
Indian Institute of Information Technology, Ranchi(印度兰契信息技术学院);Indian Institute of Science Education and Research, Berhampur(印度贝汉布尔科学教育与研究学院);Indian Institute of Science Education and Research, Mohanpur(印度莫汉布尔科学教育与研究学院);Collaborative Dynamics, Texas, United States(美国得克萨斯州协作动力公司)
Improving the State of the Art for Training Human-AI Teams: Technical Report #5 -- Individual Differences and Team Qualities to Measure in a Human-AI Teaming Testbed