超越静态快照：利用大语言模型进行群体层面价值演变的动态建模与预测
Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models
AI总结：
本文提出利用大语言模型进行群体层面价值演变的动态建模与预测方法，通过整合历史价值轨迹和事件影响，提升了社会模拟的准确性与预测能力。
摘要：
社会模拟对于挖掘复杂社会动态和支撑数据驱动决策至关重要。基于大语言模型的方法已通过利用类人社会问卷回答来建模群体行为，成为这一任务中的强大工具。现有基于大语言模型的方法大多专注于离散时间点的群体层面价值，将其视为静态快照而非动态过程。然而，群体层面的价值并非固定，而是由长期社会变化所塑造。因此，建模其动态过程对于准确的社会演变预测至关重要——这是数据挖掘和社会科学中的关键挑战。由于纵向数据有限、群体异质性以及复杂历史事件影响，这一问题仍未得到充分探索。为填补这一空白，我们提出了一种新的群体层面动态社会模拟框架，通过将历史价值轨迹整合到基于大语言模型的人类回答建模中。我们选取中国和美国作为代表性背景，跨四个核心人口社会维度（性别、年龄、教育、收入）进行分层模拟。利用世界价值观调查，我们构建了一个多波次、群体层面的纵向数据集以捕捉历史价值演变，然后提出了一种基于事件的预测方法，将社会事件、当前价值状态和群体属性统一到一个框架中。在五个大语言模型家族上的评估显示，取得了显著的提升：在已见问题上最大提升30.88%，在未见问题上提升33.97%。我们进一步发现显著的跨群体异质性：美国群体比中国群体更波动，两国年轻群体对外部变化更敏感。这些发现推进了基于大语言模型的社会模拟，并为社会科学家理解和社会预测社会价值变化提供了新的见解。
英文摘要：
Social simulation is critical for mining complex social dynamics and supporting data-driven decision making. LLM-based methods have emerged as powerful tools for this task by leveraging human-like social questionnaire responses to model group behaviors. Existing LLM-based approaches predominantly focus on group-level values at discrete time points, treating them as static snapshots rather than dynamic processes. However, group-level values are not fixed but shaped by long-term social changes. Modeling their dynamics is thus crucial for accurate social evolution prediction--a key challenge in both data mining and social science. This problem remains underexplored due to limited longitudinal data, group heterogeneity, and intricate historical event impacts. To bridge this gap, we propose a novel framework for group-level dynamic social simulation by integrating historical value trajectories into LLM-based human response modeling. We select China and the U.S. as representative contexts, conducting stratified simulations across four core sociodemographic dimensions (gender, age, education, income). Using the World Values Survey, we construct a multi-wave, group-level longitudinal dataset to capture historical value evolution, and then propose the first event-based prediction method for this task, unifying social events, current value states, and group attributes into a single framework. Evaluations across five LLM families show substantial gains: a maximum 30.88\% improvement on seen questions and 33.97\% on unseen questions over the Vanilla baseline. We further find notable cross-group heterogeneity: U.S. groups are more volatile than Chinese groups, and younger groups in both countries are more sensitive to external changes. These findings advance LLM-based social simulation and provide new insights for social scientists to understand and predict social value changes.
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。
