Research

A Shared Geometry of Difficulty in Multilingual Language Models

Stefano Civelli, Pietro Bernardelle, Nicolò Brunello, Gianluca Demartini
ACL 2026. 2026
Paper

Ideology-Based LLMs for Content Moderation

Stefano Civelli, Pietro Bernardelle, Nardiena A Pratama, Gianluca Demartini
TIST - Special Issue on Risks and Unintended Harms of Generative AI Systems. 2026
Paper

Political Advertising on Facebook During the 2022 Australian Federal Election: A Social Identity Perspective

Stefano Civelli, Pietro Bernardelle, Frank Mols, Gianluca Demartini
ICWSM 2026. 2026
Paper

Spotting Persuasion: A Low-cost Model for Persuasion Detection in Political Ads on Social Media

Elyas Meguellati, Stefano Civelli, Pietro Bernardelle, Shazia Sadiq, Gianluca Demartini
ICWSM 2026. 2026
Paper

The Impact of Persona-based Political Perspectives on Hateful Content Detection

Stefano Civelli, Pietro Bernardelle, Gianluca Demartini
TheWebConf'25: MM4SG Workshop (Best Paper Award). 2025
Paper

Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

Pietro Bernardelle, Leon Fröhling, Stefano Civelli, Riccardo Lunardi, Kevin Roitero, Gianluca Demartini
TheWebConf'25: Short Paper. 2025
PaperCode