A Decision Theoretic Framework for Measuring AI Reliance

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Guo, Ziyang, Wu, Yifan, Hartline, Jason, Hullman, Jessica
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914054752174080
author Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
author_facet Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15356
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Decision Theoretic Framework for Measuring AI Reliance
Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
Artificial Intelligence
Human-Computer Interaction
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.
title A Decision Theoretic Framework for Measuring AI Reliance
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2401.15356