65 citations · 129 across the 15 of their papers we have counts for
6 papers · 1 filter
Group size effects and collective misalignment in LLM multi-agent systems
Ariel Flint, Luca Maria Aiello, Romualdo Pastor-Satorras +1
Multi-agent systems of large language models (LLMs) are rapidly expanding across domains, introducing dynamics not captured by single-agent evaluations. Yet, existing work has most…
Reply to "Emergent LLM behaviors are observationally equivalent to data leakage"
Ariel Flint Ashery, Luca Maria Aiello, Andrea Baronchelli
A potential concern when simulating populations of large language models (LLMs) is data contamination, i.e. the possibility that training data may shape outcomes in unintended ways…
How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare
Daniel Thilo Schroeder, Meeyoung Cha, Andrea Baronchelli +19
Advances in AI offer the prospect of manipulating beliefs and behaviors on a population-wide level. Large language models and autonomous agents now let influence campaigns reach un…
Towards global equity in political polarization research
Max Falkenberg, Matteo Cinelli, Alessandro Galeazzi +18
With a folk understanding that political polarization refers to socio-political divisions within a society, many have proclaimed that we are more divided than ever. In this account…
Bootstrapping Social Networks: Lessons from Bluesky Starter Packs
Leonhard Balduf, Saidu Sokoto, Onur Ascigil +6
Microblogging is a crucial mode of online communication. However, launching a new microblogging platform remains challenging, largely due to network effects. This has resulted in e…
From Niche to Mainstream: Community Size and Engagement in Social Media Conversations
Jacopo Nudo, Matteo Cinelli, Andrea Baronchelli +1
The architecture of public discourse has been profoundly reshaped by social media platforms, which mediate interactions at an unprecedented scale and complexity. This study analyze…