LLMs生成结构上真实的社会网络，但高估了政治同质性
LLMs generate structurally realistic social networks but overestimate political homophily
AI总结：
本研究开发三种提示方法让LLM生成社会网络，发现局部方法更真实，但LLM生成网络虽在结构上匹配真实网络，却显著高估政治同质性。
摘要：
生成社会网络对于许多应用至关重要，例如流行病建模和社会模拟。生成式AI的出现，特别是大型语言模型（LLMs），为社会网络生成提供了新的可能性：LLMs无需额外训练或定义网络参数即可生成网络，用户可以通过自然语言灵活地定义网络中的个体。然而，这一潜力引发了两个关键问题：1）LLMs生成的社会网络是否真实，2）鉴于人口统计特征在形成社会联系中的重要性，存在哪些偏差风险？为回答这些问题，我们开发了三种网络生成的提示方法，并将生成的网络与一系列真实社会网络进行比较。我们发现，使用“局部”方法（LLM一次为一个角色构建关系）生成的网络比使用“全局”方法（一次性构建整个网络）生成的网络更真实。我们还发现，生成的网络在密度、聚类、连通性和度分布等许多特征上与真实网络匹配。然而，我们发现LLMs强调政治同质性超过所有其他类型的同质性，并且与真实社会网络相比，显著高估了政治同质性。
英文摘要：
Generating social networks is essential for many applications, such as epidemic modeling and social simulations. The emergence of generative AI, especially large language models (LLMs), offers new possibilities for social network generation: LLMs can generate networks without additional training or need to define network parameters, and users can flexibly define individuals in the network using natural language. However, this potential raises two critical questions: 1) are the social networks generated by LLMs realistic, and 2) what are risks of bias, given the importance of demographics in forming social ties? To answer these questions, we develop three prompting methods for network generation and compare the generated networks to a suite of real social networks. We find that more realistic networks are generated with "local" methods, where the LLM constructs relations for one persona at a time, compared to "global" methods that construct the entire network at once. We also find that the generated networks match real networks on many characteristics, including density, clustering, connectivity, and degree distribution. However, we find that LLMs emphasize political homophily over all other types of homophily and significantly overestimate political homophily compared to real social networks.
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。
