9 papers
Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision Policies
Alejandro Buitrago López, Javier Pastor-Galindo, José A. Ruipérez-Valiente
Large language models (LLMs) are increasingly used as decision-making components in social simulations. This introduces a methodological risk: the simulation may deviate from the e…
Execution and assessment of agentic influence operations in simulated social networks
Alejandro Buitrago López, David Montoro Aguilera, Javier Pastor-Galindo +1
This article evaluates AI-enabled influence operations in synthetic social networks through controlled simulations of narrative release, amplification, and counter-messaging. We me…
Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
Alejandro Buitrago López, Alberto Ortega Pastor, Javier Pastor-Galindo +1
LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has largely relied on general-pur…
Agent-based simulation of online social networks and disinformation
Alejandro Buitrago López, Alberto Ortega Pastor, David Montoro Aguilera +4
Research on online social networks (OSNs) is often hindered by platform opacity, limited access to data, and ethical constraints. Simulation offer a valuable alternative, but exist…
Synthetic generation of online social networks through homophily
Alejandro Buitrago López, Javier Pastor-Galindo, José A. Ruipérez-Valiente
Online social networks (OSNs) have become increasingly relevant for studying social behavior and information diffusion. Nevertheless, they are limited by restricted access to real…
DISINFOX: an open-source threat exchange platform serving intelligence on disinformation and influence operations
Felipe Sánchez González, Javier Pastor-Galindo, José A. Ruipérez-Valiente
This paper introduces DISINFOX, an open-source threat intelligence exchange platform for the structured collection, management, and dissemination of disinformation incidents and in…