Saved in:
Bibliographic Details
Main Authors: He, Kevin, Shorrer, Ran, Xia, Mengjia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.14708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911560984690688
author He, Kevin
Shorrer, Ran
Xia, Mengjia
author_facet He, Kevin
Shorrer, Ran
Xia, Mengjia
contents We conduct an incentivized laboratory experiment to study people's perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of risk, time preference, social preference, and strategic interactions, we ask human subjects to make choices for themselves and to predict the choices made by GenAI on behalf of a human user. We find that people overestimate the degree of alignment between GenAI and human choices. In every problem, human subjects' average prediction about GenAI's choice is substantially closer to the average human-subject choice than it is to the GenAI choice. At the individual level, different subjects' predictions about GenAI's choice in a given problem are highly correlated with their own choices in the same problem. We explore the implications of people overestimating GenAI alignment in a simple theoretical model.
format Preprint
id arxiv_https___arxiv_org_abs_2502_14708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human Misperception of Generative-AI Alignment: A Laboratory Experiment
He, Kevin
Shorrer, Ran
Xia, Mengjia
Theoretical Economics
Artificial Intelligence
Computer Science and Game Theory
We conduct an incentivized laboratory experiment to study people's perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of risk, time preference, social preference, and strategic interactions, we ask human subjects to make choices for themselves and to predict the choices made by GenAI on behalf of a human user. We find that people overestimate the degree of alignment between GenAI and human choices. In every problem, human subjects' average prediction about GenAI's choice is substantially closer to the average human-subject choice than it is to the GenAI choice. At the individual level, different subjects' predictions about GenAI's choice in a given problem are highly correlated with their own choices in the same problem. We explore the implications of people overestimating GenAI alignment in a simple theoretical model.
title Human Misperception of Generative-AI Alignment: A Laboratory Experiment
topic Theoretical Economics
Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2502.14708