arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.06111cs.AIcs.CY
收藏

由大型语言模型驱动的社会数字孪生:一种用于模拟人口对政策干预反应的框架

LLM Powered Social Digital Twins: A Framework for Simulating Population Behavioral Response to Policy Interventions

PwC(普华永道)

Fatima Koaik, Aayush Gupta, Farahan Raza Sheikh

AI总结:

本文提出了一种由大型语言模型驱动的社会数字孪生框架,用于模拟人群对政策干预的反应,通过校准层实现对真实数据的验证,并在疫情期间展示了20.7%的预测误差改进。

摘要:

预测人群对政策干预的反应是计算社会科学和公共政策中的基本挑战。传统方法依赖于汇总统计模型,这些模型捕捉历史相关性,但缺乏机制解释性,并在面对新政策场景时表现不佳。我们提出了一种通用框架,用于构建社会数字孪生——虚拟的人口复制品,其中大型语言模型(LLMs)作为个体代理的认知引擎。每个代理具有人口统计和心理图谱属性,接收政策信号并输出多维行为概率向量。校准层将聚合代理响应映射到可观察的人口层面指标,使模型能够验证与真实数据并部署用于反事实政策分析。我们在此框架的疫情期间响应领域进行了实例化,以新冠疫情为案例研究,利用丰富的观察数据。在留出的测试期,我们的校准数字孪生在六个行为类别上比梯度提升基线模型的宏平均预测误差提高了20.7%。反事实实验显示了对政策变化的单调和有界响应,建立了行为合理性。该框架是领域无关的:相同的架构适用于交通政策、经济干预、环境法规或任何政策影响人口行为的场景。我们讨论了该方法对政策模拟的影响、该方法的局限性以及将LLM驱动的数字孪生扩展到疫情以外领域的方向。

英文摘要:

Predicting how populations respond to policy interventions is a fundamental challenge in computational social science and public policy. Traditional approaches rely on aggregate statistical models that capture historical correlations but lack mechanistic interpretability and struggle with novel policy scenarios. We present a general framework for constructing Social Digital Twins - virtual population replicas where Large Language Models (LLMs) serve as cognitive engines for individual agents. Each agent, characterized by demographic and psychographic attributes, receives policy signals and outputs multi-dimensional behavioral probability vectors. A calibration layer maps aggregated agent responses to observable population-level metrics, enabling validation against real-world data and deployment for counterfactual policy analysis. We instantiate this framework in the domain of pandemic response, using COVID-19 as a case study with rich observational data. On a held-out test period, our calibrated digital twin achieves a 20.7% improvement in macro-averaged prediction error over gradient boosting baselines across six behavioral categories. Counterfactual experiments demonstrate monotonic and bounded responses to policy variations, establishing behavioral plausibility. The framework is domain-agnostic: the same architecture applies to transportation policy, economic interventions, environmental regulations, or any setting where policy affects population behavior. We discuss implications for policy simulation, limitations of the approach, and directions for extending LLM-based digital twins beyond pandemic response.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑