Social networks influence behaviors, preferences, and relationships and play
a crucial role in the dissemination of information and norms within human
societies. As large language models (LLMs) increasingly integrate into social
and professional environments, understanding their behavior within the context
of social networks and interactions becomes essential. Our study analyzes the
behaviors of standard network structures and real-world networks to determine
whether the dynamics of multiple LLMs align with human social dynamics. We
explore various social network principles, including micro-level concepts such
as preferential attachment, triadic closure, and homophily, as well as
macro-level concepts like community structure and the small-world phenomenon.
Our findings suggest that LLMs demonstrate all these principles when they are
provided with network structures and asked about their preferences regarding
network formation. Furthermore, we investigate LLMs' decision-making based on
real-world networks to compare the strengths of these principles. Our results
reveal that triadic closure and homophily have a stronger influence than
preferential attachment and that LLMs substantially exceed random guessing in
the task of network formation predictions. Overall, our study contributes to
the development of socially aware LLMs by shedding light on LLMs' network
formation behaviors and exploring their impacts on social dynamics and norms.

我们的研究分析了标准网络结构和真实世界网络的行为，以确定多个大型语言模型在人类社交动态中是否与人类社交动态一致。我们探讨了各种社交网络原则，包括微观层面的概念（如优先连接、三元闭合和同质性），以及宏观层面的概念，如社群结构和小世界现象。我们的研究结果表明，当给定网络结构并询问 LLMs 关于网络形成的偏好时，LLMs 展现了所有这些原则。此外，我们还研究了基于真实世界网络的 LLMs 决策，以比较这些原则的优势。我们的结果表明，三元闭合和同质性比优先连接具有更强的影响力，并且 LLMs 在网络形成预测任务中远远超出随机猜测。总体而言，我们的研究通过揭示 LLMs 的网络形成行为，并探索它们对社交动态和规范的影响，为开发具有社交意识的 LLMs 做出了贡献。

多 LLM 之间的网络形成与动态

Network Formation and Dynamics Among Multi-LLMs

Many prediction problems on social networks, from recommendations to anomaly
detection, can be approached by modeling network data as a sequence of
relational events and then leveraging the resulting model for prediction.
Conditional logit models of discrete choice are a natural approach to modeling
relational events as "choices" in a framework that envelops and extends many
long-studied models of network formation. The conditional logit model is
simplistic, but it is particularly attractive because it allows for efficient
consistent likelihood maximization via negative sampling, something that isn't
true for mixed logit and many other richer models. The value of negative
sampling is particularly pronounced because choice sets in relational data are
often enormous.
Given the importance of negative sampling, in this work we introduce a model
simplification technique for mixed logit models that we call "de-mixing",
whereby standard mixture models of network formation---particularly models that
mix local and global link formation---are reformulated to operate their modes
over disjoint choice sets. This reformulation reduces mixed logit models to
conditional logit models, opening the door to negative sampling while also
circumventing other standard challenges with maximizing mixture model
likelihoods. To further improve scalability, we also study importance sampling
for more efficiently selecting negative samples, finding that it can greatly
speed up inference in both standard and de-mixed models. Together, these steps
make it possible to much more realistically model network formation in very
large graphs. We illustrate the relative gains of our improvements on synthetic
datasets with known ground truth as well as a large-scale dataset of public
transactions on the Venmo platform.

通过模拟社交网络的关系事件序列，应用条件逻辑模型和负采样技术，提高网络形成的建模准确性和可扩展性。

关系社交数据的选择模型扩展

Scaling Choice Models of Relational Social Data

Social, biological and economic networks grow and decline with occasional
fragmentation and re-formation, often explained in terms of external
perturbations. We show that these phenomena can be a direct consequence of
simple imitation and internal conflicts between 'cooperators' and 'defectors'.
We employ a game-theoretic model of dynamic network formation where successful
individuals are more likely to be imitated by newcomers who adopt their
strategies and copy their social network. We find that, despite using the same
mechanism, cooperators promote well-connected highly prosperous networks and
defectors cause the network to fragment and lose its prosperity; defectors are
unable to maintain the highly connected networks they invade. Once the network
is fragmented it can be reconstructed by a new invasion of cooperators, leading
to the cycle of formation and fragmentation seen, for example, in bacterial
communities and socio-economic networks. In this endless struggle between
cooperators and defectors we observe that cooperation leads to prosperity, but
prosperity is associated with instability. Cooperation is prosperous when the
network has frequent formation and fragmentation.

本研究通过一个动态网络生成的、博弈论模型来显示，社会、生物学和经济网络的形成和衰败可以直接归因于简单的模仿和合作者与叛徒之间的内部冲突。合作者推动着连接紧密、高度繁荣的网络，而叛徒则导致网络破碎并失去繁荣。