CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models

TL;DR

CrowdLLM combines pretrained large language models and generative models to create diverse, accurate, and cost-effective digital populations that mimic real human data for various applications.

Contribution

The paper introduces CrowdLLM, a novel framework integrating LLMs and generative models to improve the diversity and fidelity of digital populations.

Findings

CrowdLLM achieves high accuracy in replicating human data.

It demonstrates scalability and cost-effectiveness.

The approach outperforms existing methods in diversity and realism.

Abstract

The emergence of large language models (LLMs) has sparked much interest in creating LLM-based digital populations that can be applied to many applications such as social simulation, crowdsourcing, marketing, and recommendation systems. A digital population can reduce the cost of recruiting human participants and alleviate many concerns related to human subject study. However, research has found that most of the existing works rely solely on LLMs and could not sufficiently capture the accuracy and diversity of a real human population. To address this limitation, we propose CrowdLLM that integrates pretrained LLMs and generative models to enhance the diversity and fidelity of the digital population. We conduct theoretical analysis of CrowdLLM regarding its great potential in creating cost-effective, sufficiently representative, scalable digital populations that can match the quality of a real crowd. Comprehensive experiments are also conducted across multiple domains (e.g., crowdsourcing, voting, user rating) and simulation studies which demonstrate that CrowdLLM achieves promising performance in both accuracy and distributional fidelity to human data.