Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans

TL;DR

This study reveals that large language models tend to portray socially subordinate groups as more homogeneous than dominant groups, reflecting a bias similar to human social perception, which could reinforce stereotypes.

Contribution

The paper identifies and analyzes a new form of bias in LLMs, showing they depict minority groups as more homogeneous, extending beyond stereotypical attribute associations.

Findings

ChatGPT portrays minority groups as more homogeneous than majority groups.

Gender differences in perceived homogeneity are small but present.

The bias varies across racial/ethnic groups and genders.

Abstract

Large language models (LLMs) are becoming pervasive in everyday life, yet their propensity to reproduce biases inherited from training data remains a pressing concern. Prior investigations into bias in LLMs have focused on the association of social groups with stereotypical attributes. However, this is only one form of human bias such systems may reproduce. We investigate a new form of bias in LLMs that resembles a social psychological phenomenon where socially subordinate groups are perceived as more homogeneous than socially dominant groups. We had ChatGPT, a state-of-the-art LLM, generate texts about intersectional group identities and compared those texts on measures of homogeneity. We consistently found that ChatGPT portrayed African, Asian, and Hispanic Americans as more homogeneous than White Americans, indicating that the model described racial minority groups with a narrower range of human experience. ChatGPT also portrayed women as more homogeneous than men, but these differences were small. Finally, we found that the effect of gender differed across racial/ethnic groups such that the effect of gender was consistent within African and Hispanic Americans but not within Asian and White Americans. We argue that the tendency of LLMs to describe groups as less diverse risks perpetuating stereotypes and discriminatory behavior.