评分 5.5 · 来源：cs.CL updates on arXiv.org · 发布于 2026-04-17
评分依据：Shows GNN can match/beat LLMs on close-ended human simulation tasks at lower cost, challenges LLM necessity assumption
arXiv:2511.02135v2 Announce Type: replace 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.