MOSAIC：多智能體模擬中的社交AI建模，用於內容傳播與監管

MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations

April 10, 2025

作者: Genglin Liu, Salman Rahman, Elisa Kreiss, Marzyeh Ghassemi, Saadia Gabriel

cs.AI

摘要

我們提出了一個新穎的開源社交網絡模擬框架MOSAIC，其中生成式語言代理能夠預測用戶行為，如點贊、分享和標記內容。該模擬結合了大型語言模型（LLM）代理與有向社交圖，以分析湧現的欺騙行為，並更好地理解用戶如何判斷在線社交內容的真實性。通過從多樣化的細粒度角色構建用戶表示，我們的系統支持多代理模擬，大規模地建模內容傳播和參與動態。在此框架內，我們評估了三種不同的內容審核策略與模擬的錯誤信息傳播，發現這些策略不僅能減緩非事實內容的擴散，還能提高用戶參與度。此外，我們分析了模擬中熱門內容的傳播軌跡，並探討了模擬代理對其社交互動的明確推理是否真正與其集體參與模式相一致。我們開源了模擬軟件，以鼓勵人工智能和社會科學領域的進一步研究。

English

We present a novel, open-source social network simulation framework, MOSAIC, where generative language agents predict user behaviors such as liking, sharing, and flagging content. This simulation combines LLM agents with a directed social graph to analyze emergent deception behaviors and gain a better understanding of how users determine the veracity of online social content. By constructing user representations from diverse fine-grained personas, our system enables multi-agent simulations that model content dissemination and engagement dynamics at scale. Within this framework, we evaluate three different content moderation strategies with simulated misinformation dissemination, and we find that they not only mitigate the spread of non-factual content but also increase user engagement. In addition, we analyze the trajectories of popular content in our simulations, and explore whether simulation agents' articulated reasoning for their social interactions truly aligns with their collective engagement patterns. We open-source our simulation software to encourage further research within AI and social sciences.