Humans expect rationality and cooperation from LLM opponents in strategic games

TL;DR

This study investigates how humans behave in strategic games against LLMs, revealing they tend to choose lower numbers and perceive LLMs as more rational and cooperative, especially among high reasoning individuals.

Contribution

First controlled experiment comparing human behavior against LLMs and humans in strategic games, highlighting differences in choices and perceptions.

Findings

Humans choose lower numbers against LLMs than humans.

High reasoning individuals are more influenced by LLMs' perceived rationality.

Subjects attribute cooperative tendencies to LLMs, affecting their strategies.

Abstract

As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. We present the results of the first controlled monetarily-incentivised laboratory experiment looking at differences in human behaviour in a multi-player p-beauty contest against other humans and LLMs. We use a within-subject design in order to compare behaviour at the individual level. We show that, in this environment, human subjects choose significantly lower numbers when playing against LLMs than humans, which is mainly driven by the increased prevalence of `zero' Nash-equilibrium choices. This shift is mainly driven by subjects with high strategic reasoning ability. Subjects who play the zero Nash-equilibrium choice motivate their strategy by appealing to perceived LLM's reasoning ability and, unexpectedly, propensity towards cooperation. Our findings provide foundational insights into the multi-player human-LLM interaction in simultaneous choice games, uncover heterogeneities in both subjects' behaviour and beliefs about LLM's play when playing against them, and suggest important implications for mechanism design in mixed human-LLM systems.