Learning to Advise Humans in High-Stakes Settings

• URL: http://arxiv.org/abs/2210.12849v3
• Date: Mon, 13 Feb 2023 16:16:47 GMT
• Title: Learning to Advise Humans in High-Stakes Settings
• Abstract summary: 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.
• Score: 8.921629768446625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making [0.0]
  We introduce a human-AI collaborative decision-making framework designed to augment human capabilities and align AI agents with human preferences and expectations.<n>The Human-Centric Reflective Architecture (HCRA) integrates human-calibrated models with reinforcement learning agents that leverage linguistic feedback in an iterative, reflective process.
  arXiv  Detail & Related papers  (2026-07-03T07:12:44Z)
• A Framework for Measuring Appropriate Reliance on Set-Valued AI Advice [4.452583096196013]
  We develop the first formal framework for measuring appropriate reliance on set-valued AI advice within the sequential judge-advisor paradigm.<n>We show how these metrics capture important nuances in human-AI collaboration that existing measures overlook.
  arXiv  Detail & Related papers  (2026-06-04T12:17:42Z)
• When Should Humans Step In? Optimal Human Dispatching in AI-Assisted Decisions [2.7755032786791003]
  We propose a general decision-theoretic framework for human-AI collaboration.<n>We treat AI assessments as factor-level signals and human judgments as costly information that can be selectively acquired.<n>We apply our framework to AI-assisted peer review.
  arXiv  Detail & Related papers  (2026-03-14T01:47:38Z)
• ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making [11.176700333939278]
  We propose a value-driven approach to personalized decision-making.<n>Human values serve as stable, transferable signals that support consistent and generalizable behavior.<n>We introduce ValuePilot, a two-phase framework consisting of a dataset generation toolkit (DGT) and a decision-making module (DMM)
  arXiv  Detail & Related papers  (2025-12-09T12:15:46Z)
• Towards a Cascaded LLM Framework for Cost-effective Human-AI Decision-Making [55.2480439325792]
  We present a cascaded LLM decision framework that adaptively delegates tasks across multiple tiers of expertise.<n>First, a deferral policy determines whether to accept the base model's answer or regenerate it with the large model.<n>Second, an abstention policy decides whether the cascade model response is sufficiently certain or requires human intervention.
  arXiv  Detail & Related papers  (2025-06-13T15:36:22Z)
• The Value of Information in Human-AI Decision-making [23.353778024330165]
  We contribute a decision-theoretic framework for characterizing the value of information.<n>We present a novel explanation technique that adapts SHAP explanations to highlight human-complementing information.<n>We show that our measure of complementary information can be used to identify which AI model will best complement human decisions.
  arXiv  Detail & Related papers  (2025-02-10T04:50:42Z)
• Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
  We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks. We show that the learned AI control system demonstrates robustness against adversarial tampering. In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
  arXiv  Detail & Related papers  (2024-07-03T15:38:57Z)
• ADESSE: Advice Explanations in Complex Repeated Decision-Making Environments [14.105935964906976]
  This work considers a problem setup where an intelligent agent provides advice to a human decision-maker. We develop an approach named ADESSE to generate explanations about the adviser agent to improve human trust and decision-making.
  arXiv  Detail & Related papers  (2024-05-31T08:59:20Z)
• Negotiating the Shared Agency between Humans & AI in the Recommender System [1.4249472316161877]
  Concerns about user agency have arisen due to the inherent opacity (information asymmetry) and the nature of one-way output (power asymmetry) on algorithms. We seek to understand how types of agency impact user perception and experience, and bring empirical evidence to refine the guidelines and designs for human-AI interactive systems.
  arXiv  Detail & Related papers  (2024-03-23T19:23:08Z)
• Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learning [10.08973043408929]
  offline reinforcement learning (RL) as a general approach for modeling human-AI decision-making. We show that people interacting with policies optimized for accuracy achieve significantly better accuracy than those interacting with any other type of AI support.
  arXiv  Detail & Related papers  (2024-03-09T13:30:00Z)
• Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Making [48.179458030691286]
  We examine three AI roles: Recommender, Analyzer, and Devil's Advocate. Our results show each role's distinct strengths and limitations in task performance, reliance appropriateness, and user experience. These insights offer valuable implications for designing AI assistants with adaptive functional roles according to different situations.
  arXiv  Detail & Related papers  (2024-03-04T07:32:28Z)
• A Decision Theoretic Framework for Measuring AI Reliance [23.353778024330165]
  Humans frequently make decisions with the aid of artificially intelligent (AI) systems. Researchers have identified ensuring that a human has appropriate reliance on an AI as a critical component of achieving complementary performance. We propose a formal definition of reliance, based on statistical decision theory, which separates the concepts of reliance as the probability the decision-maker follows the AI's recommendation.
  arXiv  Detail & Related papers  (2024-01-27T09:13:09Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)
• Rational Decision-Making Agent with Internalized Utility Judgment [91.80700126895927]
  Large language models (LLMs) have demonstrated remarkable advancements and have attracted significant efforts to develop LLMs into agents capable of executing intricate multi-step decision-making tasks beyond traditional NLP applications. This paper proposes RadAgent, which fosters the development of its rationality through an iterative framework involving Experience Exploration and Utility Learning. Experimental results on the ToolBench dataset demonstrate RadAgent's superiority over baselines, achieving over 10% improvement in Pass Rate on diverse tasks.
  arXiv  Detail & Related papers  (2023-08-24T03:11:45Z)
• Learning Complementary Policies for Human-AI Teams [22.13683008398939]
  We propose a framework for a novel human-AI collaboration for selecting advantageous course of action. Our solution aims to exploit the human-AI complementarity to maximize decision rewards.
  arXiv  Detail & Related papers  (2023-02-06T17:22:18Z)
• Doubting AI Predictions: Influence-Driven Second Opinion Recommendation [92.30805227803688]
  We propose a way to augment human-AI collaboration by building on a common organizational practice: identifying experts who are likely to provide complementary opinions. The proposed approach aims to leverage productive disagreement by identifying whether some experts are likely to disagree with an algorithmic assessment.
  arXiv  Detail & Related papers  (2022-04-29T20:35:07Z)
• Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork [54.309495231017344]
  We argue that AI systems should be trained in a human-centered manner, directly optimized for team performance. We study this proposal for a specific type of human-AI teaming, where the human overseer chooses to either accept the AI recommendation or solve the task themselves. Our experiments with linear and non-linear models on real-world, high-stakes datasets show that the most accuracy AI may not lead to highest team performance.
  arXiv  Detail & Related papers  (2020-04-27T19:06:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.