Communication Dans Un Congrès Année : 2025

SocialForge: simulating the social internet to provide realistic training against influence operations

Résumé

Social media platforms have enabled large-scale influence campaigns, impacting democratic processes. To fight against these threats, continuous training is needed. A typical training session is based on a fictive scenario describing key elements which are instantiated into a dedicated platform. Such a platform simulates social networks, which host a huge amount of content aligned with the training scenario. However, directly using Large Language Models to create appropriate content results in low content diversity due to coarse-grained and high-level scenario constraints, which compromises the trainees' immersion. We address this issue with SocialForge, a system designed to enhance the diversity and realism of the generated content while ensuring its adherence to the original scenario. Specifically, SocialForge refines and augments the initial scenario constraints by generating detailed subnarratives, personas, and events. We assess diversity, realism, and adherence to the scenario through custom evaluation protocol. We also propose an automatic method to detect erroneous constraint generation, ensuring optimal alignment of the content with the scenario. SocialForge has been used in real trainings and in several showcases, with great end-user satisfaction. We release an open-source dataset 1 generated with SocialForge for the research community.

Fichier principal
Vignette du fichier
SocialForge__simulating_the_social_internet_to_provide_realistic_training_against_influence_operations.pdf (678.69 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05170276 , version 1 (25-07-2025)

Licence

Identifiants

  • HAL Id : hal-05170276 , version 1

Citer

Ulysse Oliveri, Guillaume Gadek, Alexandre Dey, Benjamin Costé, Damien Lolive, et al.. SocialForge: simulating the social internet to provide realistic training against influence operations. ACL Industry Track, 2025, Vienna (Austria), Austria. ⟨hal-05170276⟩
111 Consultations
166 Téléchargements

Partager

  • More