用图神经网络模拟人类行为，效率远超大模型且更透明
Graph-Based Alternatives to LLMs for Human Simulation
- 将人类行为建模为异构图上的链接预测任务
- 在三个数据集上表现媲美或超越最强语言模型，参数量少千倍
- 适合需要高效、可解释行为模拟的场景
大型语言模型（LLMs）已成为模拟人类行为的主流方法，但其在所有模拟任务中是否必要尚不明确。本文研究了涵盖问卷预测到考试作答在内的多种闭合式模拟任务，发现图神经网络可匹配甚至超越强大多语言模型方法。我们提出图基人类行为模拟模型（GEMS），将闭合式模拟问题转化为个体与选择构成的异构图上的链接预测。在三个数据集和三种评估设置下，GEMS的表现与最强的基于LLM的方法相当或更优，但参数量仅为后者的千分之一。结果表明，图模型可作为高效且透明的人类行为模拟替代方案。代码已开源：https://github.com/schang-lab/gems。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。