A Decision Theoretic Framework for Measuring AI Reliance

被引:0
|
作者
Guo, Ziyang [1 ]
Wu, Yifan [1 ]
Hartline, Jason [1 ]
Hullman, Jessica [1 ]
机构
[1] Northwestern Univ, Evanston, IL 60208 USA
关键词
Machine learning; reliance; decision making; rational decision-maker;
D O I
10.1145/3630106.3658901
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Humans frequently make decisions with the aid of artificially intelligent (AI) systems. A common pattern is for the AI to recommend an action to the human who retains control over the final decision. Researchers have identified ensuring that a human has appropriate reliance on an AI as a critical component of achieving complementary performance. We argue that the current definition of appropriate reliance used in such research lacks formal statistical grounding and can lead to contradictions. 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 from challenges a human may face in differentiating the signals and forming accurate beliefs about the situation. Our definition gives rise to a framework that can be used to guide the design and interpretation of studies on human-AI complementarity and reliance. Using recent AI-advised decision making studies from literature, we demonstrate how our framework can be used to separate the loss due to mis-reliance from the loss due to not accurately differentiating the signals. We evaluate these losses by comparing to a baseline and a benchmark for complementary performance defined by the expected payoff achieved by a rational decision-maker facing the same decision task as the behavioral decision-makers.
引用
收藏
页码:221 / 236
页数:16
相关论文
共 50 条
  • [1] A DECISION-THEORETIC FRAMEWORK FOR INTEGRATING SENSORS INTO AI PLANS
    ABRAMSON, B
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1993, 23 (02): : 366 - 373
  • [2] A framework for explaining reliance on decision aids
    van Dongen, Kees
    van Maanen, Peter-Paul
    [J]. INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES, 2013, 71 (04) : 410 - 424
  • [3] On the (non-) reliance on algorithms-A decision-theoretic account
    Sinclair-Desgagne, Bernard
    [J]. JOURNAL OF MATHEMATICAL PSYCHOLOGY, 2024, 119
  • [4] Understanding User Reliance on AI in Assisted Decision-Making
    Cao S.
    Huang C.-M.
    [J]. Proceedings of the ACM on Human-Computer Interaction, 2022, 6 (CSCW2)
  • [5] Decision theoretic framework for NLOS identification
    Borras, J
    Hatrack, P
    Mandayam, NB
    [J]. 48TH IEEE VEHICULAR TECHNOLOGY CONFERENCE, VOLS 1-3, 1998, : 1583 - 1587
  • [6] A DECISION THEORETIC FRAMEWORK FOR APPROXIMATING CONCEPTS
    YAO, YY
    WONG, SKM
    [J]. INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1992, 37 (06): : 793 - 809
  • [7] A Conceptual Model of Trust, Perceived Risk, and Reliance on AI Decision Aids
    Solberg, Elizabeth
    Kaarstad, Magnhild
    Eitrheim, Maren H. Ro
    Bisio, Rossella
    Reegard, Kine
    Bloch, Marten
    [J]. GROUP & ORGANIZATION MANAGEMENT, 2022, 47 (02) : 187 - 222
  • [8] TRANSPORT POLICY DECISION ANALYSIS - DECISION-THEORETIC FRAMEWORK
    KHAN, AM
    [J]. SOCIO-ECONOMIC PLANNING SCIENCES, 1971, 5 (02) : 159 - 171
  • [9] A FRAMEWORK FOR EXPLAINING DECISION-THEORETIC ADVICE
    KLEIN, DA
    SHORTLIFFE, EH
    [J]. ARTIFICIAL INTELLIGENCE, 1994, 67 (02) : 201 - 243
  • [10] A DECISION-THEORETIC FRAMEWORK FOR COMPARING HEURISTICS
    GOLDEN, BL
    ASSAD, AA
    [J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 1984, 18 (02) : 167 - 171