用人口普查数据和大模型生成虚拟人群，模拟社会实验。
Agentic Society: Merging skeleton from real world and texture from Large Language Model
- 结合真实人口数据与大模型，生成带社会属性的虚拟个体。
- 生成人物具备多样性，适合模拟复杂人类行为。
- 方法避免隐私问题，但真实统计性仍有限。
近年来，大语言模型（LLMs）与智能体技术为社会科学研究实验的模拟提供了新可能，但真实世界人群数据的获取仍是一大挑战。本文提出一种新框架，利用人口普查数据与大模型生成虚拟人群，显著降低资源需求，并规避真实数据带来的隐私合规问题，同时保持一定的统计真实性。基于真实人口普查数据，该方法首先生成反映人口统计特征的个体身份（persona），再利用大模型通过类图像生成的技术手段，为这些身份注入丰富的细节。此外，我们提出基于五大性格特质测试（Big Five model）的评估框架，以检验大模型在生成个体时的能力，进一步提升生成人物的深度与逼真度。初步实验表明，该方法可生成具有多样性的虚拟个体，适用于模拟社会科学研究中的复杂人类行为。然而，评估结果显示，当前大模型仅能产生微弱的统计真实性信号。研究还揭示了大模型在对齐人类价值观与反映真实世界复杂性之间存在的张力。后续需要更全面严格的测试。代码已开源：https://github.com/baiyuqi/agentic-society.git
原文摘要 · Abstract (English)
Recent advancements in large language models (LLMs) and agent technologies offer promising solutions to the simulation of social science experiments, but the availability of data of real-world population required by many of them still poses as a major challenge. This paper explores a novel framework that leverages census data and LLMs to generate virtual populations, significantly reducing resource requirements and bypassing privacy compliance issues associated with real-world data, while keeping a statistical truthfulness. Drawing on real-world census data, our approach first generates a persona that reflects demographic characteristics of the population. We then employ LLMs to enrich these personas with intricate details, using techniques akin to those in image generative models but applied to textual data. Additionally, we propose a framework for the evaluation of the feasibility of our method with respect to capability of LLMs based on personality trait tests, specifically the Big Five model, which also enhances the depth and realism of the generated personas. Through preliminary experiments and analysis, we demonstrate that our method produces personas with variability essential for simulating diverse human behaviors in social science experiments. But the evaluation result shows that only weak sign of statistical truthfulness can be produced due to limited capability of current LLMs. Insights from our study also highlight the tension within LLMs between aligning with human values and reflecting real-world complexities. Thorough and rigorous test call for further research. Our codes are released at https://github.com/baiyuqi/agentic-society.git
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。