Observing Micromotives and Macrobehavior of Large Language Models

TL;DR

This paper applies Schelling's segregation model to large language models to explore how individual biases in LLMs can lead to societal-level segregation, revealing that societal segregation can occur regardless of bias levels.

Contribution

It introduces a systematic study of LLMs' influence on societal macrobehavior using Schelling's model, highlighting the impact of LLM suggestions on societal segregation.

Findings

Highly segregated societies emerge as more people follow LLM suggestions.

Segregation occurs regardless of the bias level in LLMs.

Calls for reevaluating assumptions about bias mitigation in LLMs.

Abstract

Thomas C. Schelling, awarded the 2005 Nobel Memorial Prize in Economic Sciences, pointed out that ``individuals decisions (micromotives), while often personal and localized, can lead to societal outcomes (macrobehavior) that are far more complex and different from what the individuals intended.'' The current research related to large language models' (LLMs') micromotives, such as preferences or biases, assumes that users will make more appropriate decisions once LLMs are devoid of preferences or biases. Consequently, a series of studies has focused on removing bias from LLMs. In the NLP community, while there are many discussions on LLMs' micromotives, previous studies have seldom conducted a systematic examination of how LLMs may influence society's macrobehavior. In this paper, we follow the design of Schelling's model of segregation to observe the relationship between the micromotives and macrobehavior of LLMs. Our results indicate that, regardless of the level of bias in LLMs, a highly segregated society will emerge as more people follow LLMs' suggestions. We hope our discussion will spark further consideration of the fundamental assumption regarding the mitigation of LLMs' micromotives and encourage a reevaluation of how LLMs may influence users and society.