People will agree what I think: Investigating LLM's False Consensus Effect

TL;DR

This paper investigates whether large language models exhibit the false consensus effect, a human cognitive bias, and how different prompts influence this bias, revealing that LLMs do demonstrate FCE under certain conditions.

Contribution

The study provides the first thorough examination of false consensus effect in LLMs, considering confounding biases and prompt variations, and identifies conditions affecting FCE prevalence.

Findings

LLMs exhibit false consensus effect

Prompt styles influence FCE expression in LLMs

FCE prevalence varies with usage conditions

Abstract

Large Language Models (LLMs) have been recently adopted in interactive systems requiring communication. As the false belief in a model can harm the usability of such systems, LLMs should not have cognitive biases that humans have. Psychologists especially focus on the False Consensus Effect (FCE), a cognitive bias where individuals overestimate the extent to which others share their beliefs or behaviors, because FCE can distract smooth communication by posing false beliefs. However, previous studies have less examined FCE in LLMs thoroughly, which needs more consideration of confounding biases, general situations, and prompt changes. Therefore, in this paper, we conduct two studies to examine the FCE phenomenon in LLMs. In Study 1, we investigate whether LLMs have FCE. In Study 2, we explore how various prompting styles affect the demonstration of FCE. As a result of these studies, we identified that popular LLMs have FCE. Also, the result specifies the conditions when FCE becomes more or less prevalent compared to normal usage.