{"ID":2846912,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.02135","arxiv_id":"2511.02135","title":"Graph-Based Alternatives 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.","short_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 ma...","url_abs":"https://arxiv.org/abs/2511.02135","url_pdf":"https://arxiv.org/pdf/2511.02135v2","authors":"[\"Joseph Suh\",\"Suhong Moon\",\"Serina Chang\"]","published":"2025-11-03T23:54:24Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Graph Neural Network\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":607469,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2846912,"paper_url":"https://arxiv.org/abs/2511.02135","paper_title":"Graph-Based Alternatives to LLMs for Human Simulation","repo_url":"https://github.com/schang-lab/gems","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}