A Decision Theoretic Framework for Measuring AI Reliance

TL;DR

This paper introduces a formal, decision-theoretic framework for measuring human reliance on AI, distinguishing between reliance probability and signal differentiation challenges, to improve understanding of human-AI complementarity.

Contribution

It provides a statistically grounded definition of reliance and a framework to analyze human-AI decision-making, addressing limitations of previous informal approaches.

Findings

Framework separates reliance from signal differentiation issues

Demonstrates application to existing AI decision-making studies

Defines benchmarks for evaluating human-AI complementarity

Abstract

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.