Human Misperception of Generative-AI Alignment: A Laboratory Experiment

TL;DR

This study experimentally investigates how people perceive the alignment of generative AI with human preferences, revealing a tendency to overestimate AI-human alignment across various decision-making domains.

Contribution

It provides empirical evidence that humans overestimate GenAI alignment and explores the implications through a theoretical model.

Findings

People overestimate GenAI alignment in economic decision tasks.

Predictions about GenAI are closer to human choices than to AI choices.

Individuals' predictions correlate with their own choices.

Abstract

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.