The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents

TL;DR

This paper investigates whether LLM-based agents can exhibit human-like collective intelligence and partisan bias, finding they can converge on accurate beliefs but are affected by prompting strategies and data tuning.

Contribution

It demonstrates that LLM agents can mimic human partisan group behavior and explores factors influencing their collective decision-making dynamics.

Findings

LLM agents display human-like partisan biases.

Agents converge to more accurate beliefs through deliberation.

Fine-tuning improves convergence.

Abstract

Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias -- a phenomenon known as the "wisdom of partisan crowds." Generated agents powered by Large Language Models (LLMs) are increasingly used to simulate human collective behavior, yet few benchmarks exist for evaluating their dynamics against the behavior of human groups. In this paper, we examine the extent to which the wisdom of partisan crowds emerges in groups of LLM-based agents that are prompted to role-play as partisan personas (e.g., Democrat or Republican). We find that they not only display human-like partisan biases, but also converge to more accurate beliefs through deliberation as humans do. We then identify several factors that interfere with convergence, including the use of chain-of-thought prompt and lack of details in personas. Conversely, fine-tuning on human data appears to enhance convergence. These findings show the potential and limitations of LLM-based agents as a model of human collective intelligence.