A Bayesian Framework for Human-AI Collaboration: Complementarity and Correlation Neglect

TL;DR

This paper introduces a Bayesian decision-theoretic model to analyze human-AI collaboration, focusing on how information overlap and behavioral biases like correlation neglect influence decision outcomes.

Contribution

It develops a micro-founded measure of informational overlap and characterizes the impact of correlation neglect on human-AI decision regimes.

Findings

AI assistance's effectiveness depends on informational overlap.

Correlation neglect can impair decision quality despite AI recommendations.

The model delineates conditions for augmentation, impairment, and complementarity.

Abstract

We develop a decision-theoretic model of human-AI interaction to study when AI assistance improves or impairs human decision-making. A human decision-maker observes private information and receives a recommendation from an AI system, but may combine these signals imperfectly. We show that the effect of AI assistance decomposes into two main forces: the marginal informational value of the AI beyond what the human already knows, and a behavioral distortion arising from how the human uses the AI's recommendation. Central to our analysis is a micro-founded measure of informational overlap between human and AI knowledge. We study an empirically relevant form of imperfect decision-making -- correlation neglect -- whereby humans treat AI recommendations as independent of their own information despite shared evidence. Under this model, we characterize how overlap and AI capabilities shape the Human-AI interaction regime between augmentation, impairment, complementarity, and automation, and draw key insights.