Davide Ghilardi

According to our database, Davide Ghilardi authored at least 3 papers between 2024 and 2025.

Collaborative distances:

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

2025

h4rm3l: A Language for Composable Jailbreak Attack Synthesis.

Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi, Dan Jurafsky, Christopher D. Manning

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups.

Davide Ghilardi, Federico Belotti, Marco Molinari

CoRR, 2024

h4rm3l: A Dynamic Benchmark of Composable Jailbreak Attacks for LLM Safety Assessment.

Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi, Dan Jurafsky, Christopher D. Manning

CoRR, 2024