Poster by francesco croce Papers
3 papers found
Is In-Context Learning Sufficient for Instruction Following in LLMs?
Hao Zhao, Maksym Andriushchenko, francesco croce et al.
ICLR 2025poster
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Maksym Andriushchenko, francesco croce, Nicolas Flammarion
ICLR 2025poster
375
citations
Selective induction Heads: How Transformers Select Causal Structures in Context
Francesco D'Angelo, francesco croce, Nicolas Flammarion
ICLR 2025poster