Most Cited 2025 Poster by francesco croce Papers
3 papers found
Conference
#1
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Maksym Andriushchenko, francesco croce, Nicolas Flammarion
ICLR 2025posterarXiv:2404.02151
387
citations
#2
Is In-Context Learning Sufficient for Instruction Following in LLMs?
Hao Zhao, Maksym Andriushchenko, francesco croce et al.
ICLR 2025posterarXiv:2405.19874
21
citations
#3
Selective induction Heads: How Transformers Select Causal Structures in Context
Francesco D'Angelo, francesco croce, Nicolas Flammarion
ICLR 2025posterarXiv:2509.08184
5
citations