Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMs

Pengda Wang, Zilin Xiao, Hanjie Chen, Frederick L. Oswald

Research Area: Human mind, brain, philosophy, laws and LMs

Keywords: Psychology, Representativeness Heuristic, Language Models

TL;DR: Dissecting Representativeness Heuristic in Language Models

Abstract: Although large language models (LLMs) have demonstrated remarkable proficiency in modeling text and generating human-like text, they may exhibit biases acquired from training data in doing so. Specifically, LLMs may be susceptible to a common cognitive trap in human decision-making called the representativeness heuristic. This is a concept in psychology that refers to judging the likelihood of an event based on how closely it resembles a well-known prototype or typical example, versus considering broader facts or statistical evidence. This research investigates the impact of the representativeness heuristic on LLM reasoning. We created ReHeAT (Representativeness Heuristic AI Testing), a dataset containing a series of problems spanning six common types of representativeness heuristics. Experiments reveal that four LLMs applied to ReHeAT all exhibited representativeness heuristic biases. We further identify that the model's reasoning steps are often incorrectly based on a stereotype rather than on the problem's description. Interestingly, the performance improves when adding a hint in the prompt to remind the model to use its knowledge. This suggests the uniqueness of the representativeness heuristic compared to traditional biases. It can occur even when LLMs possess the correct knowledge while falling into a cognitive trap. This highlights the importance of future research focusing on the representativeness heuristic in model reasoning and decision-making and on developing solutions to address it.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 27