Emergence of Scale-Free Networks in Social Interactions among Large Language Models
Giordano De Marzo1,2,3,41234{}^{1,2,3,4}start_FLOATSUPERSCRIPT 1 , 2 , 3 , 4 end_FLOATSUPERSCRIPT, Luciano Pietronero11{}^{1}start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT and David Garcia2,525{}^{2,5}start_FLOATSUPERSCRIPT 2 , 5 end_FLOATSUPERSCRIPT 11{}^{1}start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPTCentro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy. 22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTComplexity Science Hub Vienna, Josefstaedter Strasse 39, 1080, Vienna, Austria. 33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPTDipartimento di Fisica Università “Sapienza”, P.le A. Moro, 2, I-00185 Rome, Italy. 44{}^{4}start_FLOATSUPERSCRIPT 4 end_FLOATSUPERSCRIPTSapienza School for Advanced Studies, “Sapienza”, P.le A. Moro, 2, I-00185 Rome, Italy. 55{}^{5}start_FLOATSUPERSCRIPT 5 end_FLOATSUPERSCRIPTUniversity of Konstanz, Universitätstraße 10, 78457 Konstanz, Germany
Abstract
Scale-free networks are one of the most famous examples of emergent behavior and are ubiquitous in social systems, especially online social media in which users can follow each other. By analyzing the interactions of multiple generative agents using GPT3.5-turbo as a language model, we demonstrate their ability to not only mimic individual human linguistic behavior but also exhibit collective phenomena intrinsic to human societies, in particular the emergence of scale-free networks. We discovered that this process is disrupted by a skewed token prior distribution of GPT3.5-turbo, which can lead to networks with extreme centralization as a kind of alignment. We show how renaming agents removes these token priors and allows the model to generate a range of networks from random networks to more realistic scale-free networks.
中文速览
大型语言模型驱动的多个智能体能否像人类一样通过互动自发形成复杂的社交网络，是这项研究要回答的问题。研究者用 GPT-3.5-turbo 充当生成式智能体，让新加入的“用户”根据其他用户的连接数选择关注对象，并反复扩展网络，同时通过随机改名检验模型对名称的词元偏好。结果显示，智能体在看到连接数且消除名称偏差后，会形成具有幂律度分布的无标度网络（scale-free network），表现出类似人类网络的线性择优连接；若隐藏连接数则更接近随机网络，而保留名称偏好时则会异常集中成少数超级中心。研究说明，LLM 不仅能模仿个体语言行为，也可能在群体互动中产生社会层面的涌现现象，但模型自身的词元偏见会扭曲结果，这为用 LLM 构建社会仿真和评估 AI 社交系统提供了重要提醒。
原文 arXiv:2312.06619;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2312.06619v1