Saved in:
Bibliographic Details
Main Authors: Suh, Joseph, Moon, Suhong, Chang, Serina
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.02135
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913037768720384
author Suh, Joseph
Moon, Suhong
Chang, Serina
author_facet Suh, Joseph
Moon, Suhong
Chang, Serina
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-Based Alternatives to LLMs for Human Simulation
Suh, Joseph
Moon, Suhong
Chang, Serina
Computation and Language
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.
title Graph-Based Alternatives to LLMs for Human Simulation
topic Computation and Language
url https://arxiv.org/abs/2511.02135