Agentic Society：融合来自现实世界的骨架与大语言模型的纹理
Agentic Society: Merging skeleton from real world and texture from Large Language Model
AI总结：
针对社会科学模拟中真实人口数据难获取的问题，提出结合人口普查数据与LLM生成虚拟人口的Agentic Society框架，经大五人格测试验证生成画像具备行为差异性，但当前LLM仅能实现微弱统计真实性。
摘要：
大语言模型（LLM）与智能体技术的最新进展为社会科学实验的模拟提供了颇具前景的解决方案，但其中许多方法所需的真实人口数据的可获取性仍是一大挑战。本文探索了一种新颖的框架，该框架利用人口普查数据与大语言模型生成虚拟人口，在保持统计真实性的同时，大幅降低了资源需求，并规避了与真实世界数据相关的隐私合规问题。\n基于真实世界的人口普查数据，我们的方法首先生成能够反映人口统计特征的人物画像。随后，我们采用大语言模型为这些人物画像补充丰富的精细细节，所使用的技术与图像生成模型中的技术类似，但应用于文本数据。此外，我们提出了一个框架，用于基于人格特质测试（具体为大五人格模型）评估我们的方法在大语言模型能力维度上的可行性，这一框架也提升了生成的人物画像的深度与真实感。\n通过初步实验与分析，我们证明了我们的方法生成的人物画像具备社会科学实验中模拟多样化人类行为所必需的差异性。但评估结果显示，由于当前大语言模型的能力有限，仅能产生微弱的统计真实性迹象。我们的研究得出的见解也凸显了大语言模型在对齐人类价值观与反映真实世界复杂性之间的矛盾。全面且严格的测试有待进一步研究。我们的代码已发布于https://github.com/baiyuqi/agentic-society.git
英文摘要：
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
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。
