面向基于大语言模型的社会模拟的人口对齐人设生成
Population-Aligned Persona Generation for LLM-based Social Simulation
AI总结：
针对大语言模型社会模拟中缺乏真实代表性人设集的问题，提出从社交媒体生成人设、质量过滤、重要性采样全局对齐及任务适配的系统框架，显著降低人口偏差，支撑准确灵活的社会模拟。
摘要：
大语言模型（LLM）的最新进展已能实现规模和保真度前所未有的类人社会模拟，为计算社会科学提供了新机遇。然而，一个关键挑战是构建能真实代表现实人群多样性与分布的人设集。现有多数基于LLM的社会模拟研究主要聚焦于设计智能体框架和模拟环境，往往忽视了人设生成的复杂性，以及不具代表性的人设集可能引入的偏差。本文提出一个系统性框架，用于为LLM驱动的社会模拟合成高质量、与人口对齐的人设集。我们的方法首先利用LLM从长期社交媒体数据生成叙事式人设，随后通过严格的质量评估筛除低保真档案。接着我们应用重要性采样，实现与参考心理测量分布（如大五人格特质）的全局对齐。为满足特定模拟场景的需求，我们进一步引入一个任务特定模块，将全局对齐的人设集适配到目标子群体。大量实验表明，我们的方法显著降低了人口层面的偏差，可为广泛的研究和政策应用实现准确、灵活的社会模拟。
英文摘要：
Recent advances in large language models (LLMs) have enabled human-like social simulations at unprecedented scale and fidelity, offering new opportunities for computational social science. A key challenge, however, is the construction of persona sets that authentically represent the diversity and distribution of real-world populations. Most existing LLM-based social simulation studies focus primarily on designing agentic frameworks and simulation environments, often overlooking the complexities of persona generation and the potential biases introduced by unrepresentative persona sets. In this paper, we propose a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation. Our approach begins by leveraging LLMs to generate narrative personas from long-term social media data, followed by rigorous quality assessment to filter out low-fidelity profiles. We then apply importance sampling to achieve global alignment with reference psychometric distributions, such as the Big Five personality traits. To address the needs of specific simulation contexts, we further introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations. Extensive experiments demonstrate that our method significantly reduces population-level bias and enables accurate, flexible social simulation for a wide range of research and policy applications.
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。
