People will agree what I think: Investigating LLM's False Consensus Effect
This addresses a problem for developers of interactive LLM-based systems, as FCE can harm usability by introducing false beliefs, though the work is incremental in extending psychological bias studies to LLMs.
The paper investigates whether large language models (LLMs) exhibit the False Consensus Effect (FCE), a cognitive bias where individuals overestimate how much others share their beliefs, and finds that popular LLMs do show FCE, with results specifying conditions affecting its prevalence.
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.