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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Amin, Saurabh, Bennouna, Amine, Huttenlocher, Daniel, Kong, Dingwen, Lyu, Liang, Ozdaglar, Asuman
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917275673559040
author Amin, Saurabh
Bennouna, Amine
Huttenlocher, Daniel
Kong, Dingwen
Lyu, Liang
Ozdaglar, Asuman
author_facet Amin, Saurabh
Bennouna, Amine
Huttenlocher, Daniel
Kong, Dingwen
Lyu, Liang
Ozdaglar, Asuman
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14331
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Bayesian Framework for Human-AI Collaboration: Complementarity and Correlation Neglect
Amin, Saurabh
Bennouna, Amine
Huttenlocher, Daniel
Kong, Dingwen
Lyu, Liang
Ozdaglar, Asuman
Computer Science and Game Theory
Human-Computer Interaction
Theoretical Economics
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.
title A Bayesian Framework for Human-AI Collaboration: Complementarity and Correlation Neglect
topic Computer Science and Game Theory
Human-Computer Interaction
Theoretical Economics
url https://arxiv.org/abs/2602.14331