Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Enhancing Debunking Effectiveness through LLM-based Personality Adaptation
Pietro Dell'Oglio, Alessandro Bondielli, Francesco Marcelloni +1
This study proposes a novel methodology for generating personalized fake news debunking messages by prompting Large Language Models (LLMs) with persona-based inputs aligned to the…
cs.AI2025
Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations
Giacomo Fidone, Lucia Passaro, Riccardo Guidotti
Online Social Networks (OSNs) widely adopt content moderation to mitigate the spread of abusive and toxic discourse. Nonetheless, the real effectiveness of moderation interventions…