探索大模型驱动社会模拟的设计空间，揭示关键参数对结果的影响
The $\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations
- 系统分析大模型选择与连接方式对社会模拟的影响
- 发现不同参数间存在非线性交互，模型选择影响最显著
- 适合研究社会仿真、大模型应用的学者和开发者参考
随着基于大语言模型的虚拟社会（Silicon Societies）研究增多，仅使用大模型的社会网络已开始出现在非受控场景中。然而，这类网络的设计空间尚未得到充分研究，导致模型真实性的验证存在缺口。为帮助未来研究做出更明智的设计决策，本文对模拟社会网络中的关键设计选择进行了系统分析，包括用于建模个体代理的基础模型选择及其相互连接方式。以问卷调查作为代理来衡量代理观点，研究发现设计空间的结构非平凡：部分参数呈叠加效应，而其他参数则表现出复杂交互。特别地，基础大模型的选择是影响模拟结果最重要的变量。
原文摘要 · Abstract (English)
Studies attempting to simulate human behavior with $\textit{Silicon Societies}$ grow in numbers while LLM-only social networks have started appearing outside of controlled settings. However, the design space of these networks remains under-studied, which contributes to a gap in validating model realism. To enable future works to make more informed design decisions, we perform a systematic analysis of the consequences and interactions of key design choices in simulated social networks, including the choice of base model used to model individual agents, and how they are connected to each other. Using surveys as a proxy for agent opinions, our findings suggest that the geometry of the design space is non-trivial, with some parameters behaving in additive ways while others display more complex interactions. In particular, the choice of the base LLM is the most important variable impacting the simulation outcomes.
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。