Graph-Based Alternatives to LLMs for Human Simulation

TL;DR

This paper demonstrates that graph neural networks can effectively simulate human behaviors, matching or surpassing large language models while being more efficient and transparent, across various tasks and datasets.

Contribution

The authors introduce GEMS, a graph-based model for human simulation that outperforms LLMs in accuracy and efficiency on multiple datasets.

Findings

GEMS matches or exceeds LLM performance on three datasets.

GEMS uses three orders of magnitude fewer parameters than LLMs.

Graph-based models can be a viable alternative to LLMs for human simulation.

Abstract

Large language models (LLMs) have become a popular approach for simulating human behaviors, yet it remains unclear if LLMs are necessary for all simulation tasks. We study a broad family of close-ended simulation tasks, with applications from survey prediction to test-taking, and show that a graph neural network can match or surpass strong LLM-based methods. We introduce Graph-basEd Models for Human Simulation (GEMS) which formulates close-ended simulation as link prediction on a heterogeneous graph of individuals and choices. Across three datasets and three evaluation settings, GEMS matches or outperforms the strongest LLM-based methods while using three orders of magnitude fewer parameters. These results suggest that graph-based modeling can complement LLMs as an efficient and transparent approach to simulating human behaviors. Code is available at https://github.com/schang-lab/gems.