Andrea Ermellino

According to our database, Andrea Ermellino authored at least 4 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Safe-Unsafe Concept Separation Emerges from a Single Direction in Language Models Activation Space.

Andrea Ermellino, Lorenzo Malandri, Fabio Mercorio, Antonio Serino

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

2025

When Fundamental Rights Meet Artificial Intelligence: an Extended Framework for Impact Assessment in the Age of Generative AI.

Andrea Cosentini, Oreste Pollicino, Giovanni De Gregorio, Andrea Ermellino, Dario Fontanella, Nicole Inverardi, Federica Paolucci, Ilaria Penco, Daniele Regoli, Silvia Tessaro Trapani

Proceedings of the International Joint Conference on Neural Networks, 2025

A Survey on Human Resource Management Under the AI Act: Ethical, Practical, and Regulatory Perspectives.

Nicola Alboré, Alessandro Castelnovo, Matteo Della Valle, Andrea Ermellino, Luca Puggini, Silvia Tessaro

Proceedings of the 2nd Workshop on AI bias: Measurements, 2025

2024

An approach to Evaluative AI through Large Language Models.

Andrea Ermellino, Lorenzo Malandri, Fabio Mercorio, Navid Nobani, Antonio Serino

MAI-XAI@ECAI, 2024