用于人口模拟的混合人设语言模型
Mixture-of-Personas Language Models for Population Simulation
AI总结：
本文提出混合人设（MoP）概率提示方法，通过随机选择人设与示例来引导LLM生成符合目标人群行为多样性的模拟数据，无需微调且可跨模型迁移，实验表明其在合成数据生成的对齐度与多样性指标上优于现有方法。
摘要：
大型语言模型（LLMs）的进展为其在人类行为模拟等多个领域的新兴应用铺平了道路，在这些应用中，LLMs可以在社会科学研究和机器学习模型训练中增强人类生成的数据。然而，由于个体和群体之间固有的差异性，预训练的LLMs往往无法捕捉目标人群的行为多样性。为了解决这一问题，我们提出了Mixture of Personas（MoP），这是一种概率提示方法，使LLM的响应与目标人群对齐。MoP是一个上下文混合模型，其中每个组件都是一个由人设和代表子群体行为的示例所刻画的LM智能体。人设和示例根据学习到的混合权重随机选择，以在模拟过程中引出多样化的LLM响应。MoP具有灵活性，无需模型微调，并且可跨基础模型迁移。合成数据生成的实验表明，MoP在对齐度和多样性指标上优于竞争方法。
英文摘要：
Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-generated data in social science research and machine learning model training. However, pretrained LLMs often fail to capture the behavioral diversity of target populations due to the inherent variability across individuals and groups. To address this, we propose \textit{Mixture of Personas} (MoP), a \textit{probabilistic} prompting method that aligns the LLM responses with the target population. MoP is a contextual mixture model, where each component is an LM agent characterized by a persona and an exemplar representing subpopulation behaviors. The persona and exemplar are randomly chosen according to the learned mixing weights to elicit diverse LLM responses during simulation. MoP is flexible, requires no model finetuning, and is transferable across base models. Experiments for synthetic data generation show that MoP outperforms competing methods in alignment and diversity metrics.
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。
