4 papers
Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems
Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua +7
Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias exa…
The Collective Turing Test: Large Language Models Can Generate Realistic Multi-User Discussions
Azza Bouleimen, Giordano De Marzo, Taehee Kim +5
Large Language Models (LLMs) offer new avenues to simulate online communities and social media. Potential applications range from testing the design of content recommendation algor…
Dynamics of toxic behavior in the Covid-19 vaccination debate
Azza Bouleimen, Nicolò Pagan, Stefano Cresci +2
In this paper, we study the behavior of users on Online Social Networks in the context of Covid-19 vaccines in Italy. We identify two main polarized communities: Provax and Novax.…
User's Reaction Patterns in Online Social Network Communities
Azza Bouleimen, Nicolò Pagan, Stefano Cresci +3
Several one-fits-all intervention policies were introduced by the Online Social Networks (OSNs) platforms to mitigate potential harms. Nevertheless, some studies showed the limited…