The study examines how generative AI (genAI) can subtly influence collective opinion dynamics by acting as an 'invisible hand.' Using a large-scale simulation of 50,000 group discussions on 50 controversial statements with three large language models (LLMs), the researchers varied LLM agreeableness and personalization to assess their impact in homogeneous versus heterogeneous groups. Results show that profile-specific personalization boosts LLM influence when the model takes a non-neutral stance, while neutral LLMs exert a stronger effect in homogeneous groups, leading to hypotheses on the joint role of AI features and social configurations in shaping collective opinions.
By Thomas Grisold, Johannes Schneider
arXiv:2604.11312v3 Announce Type: replace-cross
Abstract: Large Language Models are increasingly deployed as interacting agents in settings such as online platforms, recommendation systems, and multi...
By Erica Cau, Andrea Failla, Giulio Rossetti
The paper investigates how large language model agents on the open platform Moltbook represent humans, focusing on human-directed stereotypes. Using an annotation framework with four dimensions—morality, friendliness, competence, and autonomy—and a subtype scheme for other attributions, the study finds that competence is the dominant evaluation, while many other attributions describe humans as epistemic, cultural, or embodied subjects. The authors also analyze how these representations appear in narrative contexts and platform-level circulation, noting that community feedback is better explained by exposure, author visibility, and content selection rather than stable insider–outsider dynamics.
By Huangchen Xu, Yuan Wu, Yi Chang
arXiv:2509.24877v3 Announce Type: replace
Abstract: The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform hum...
By Xiao Jia, Zhanzhan Zhao
The paper proposes a Friedkin‑Johnsen based framework to identify influential users in online social networks and assess how they shape community opinion. By manipulating initial opinions in experiments, the authors show that top influencers can significantly shift overall community sentiment, and their influence extends beyond direct neighbors to second‑degree contacts. The framework is validated on a tweet dataset from the U.S. presidential election, illustrating the power of digital influencers to alter public opinion.
By Omran Berjawi, Rida Khatoun, Giuseppe Fenza
The studying of opinion dynamics and its propagation within social networks is crucial for addressing a wide range of challenges, including political polarization, public health, and marketing strateg...
The study audits 576 LLM-based social simulations from 350 papers using the PIMMUR framework, which evaluates agent profile, interaction, memory, minimal control, unawareness, and realism. Results show that PIMMUR principles are met more often than minimal control, unawareness, and realism, with frontier LLMs correctly identifying the underlying experiment in 65.2% of cases and half of prompts pre‑determining outcomes. Reproducing five experiments revealed that many reported collective phenomena disappear or reverse when PIMMUR principles are enforced, suggesting that apparent emergent behaviors may be methodological artifacts rather than genuine social dynamics.
By Jiaxu Zhou, Jen-tse Huang, Xuhui Zhou, Man Ho Lam, Xintao Wang, Hao Zhu, Wenxuan Wang, Maarten Sap
arXiv:2606.30085v2 Announce Type: replace
Abstract: Large-language models have proven to be remarkable if inconsistent parrots of public attitudes and opinions. The extent to which LLMs are able to p...
By Xiangyu Ma, Mengmi Zhang, Shannon Ang, Minne Chen
arXiv:2506. 12078v2 Announce Type: replace-cross Abstract: Understanding the dynamic evolution of complex social phenomena requires both high-fidelity modeling of human behavior and large-scale simulations.
By Haoxiang Guan, Jiyan He, Liyang Fan, Zhenzhen Ren, Shaobin He, Xin Yu, Yuan Chen, Xueyin Xu, Shuxin Zheng, Yan Gao, Enhong Chen, Tie-Yan Liu, Zhen Liu
arXiv:2606. 08076v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.
By Esra D\"onmez, Agnieszka Falenska
The paper reviews how large language models (LLMs) are being used to model social networks, highlighting their ability to represent users, relationships, and interactions through natural language. It categorizes existing work into network generative models—split into selection‑based and interaction‑based approaches—and dynamic process models, which cover opinion dynamics, information diffusion, and rumor propagation. The survey also discusses the advantages of LLMs for realistic, context‑aware social behavior, while noting limitations such as social biases and prompt sensitivity, and outlines open research challenges and future directions.
By Shikha Mallick, Alex Thomo, Akrati Saxena
arXiv:2409. 01754v4 Announce Type: replace-cross Abstract: From the printing press to social media, innovations in communication technology have repeatedly reshaped how ideas spread through human culture.
By Hiromu Yakura, Ezequiel Lopez-Lopez, Levin Brinkmann, Ignacio de la Serna, Lara Kirfel, Prateek Gupta, Ivan Soraperra, Thomas F. Eisenmann, Dirk U. Wulff, Iyad Rahwan