Papers by Amit LeVi

1 papers
Jailbreak Attack Initializations as Extractors of Compliance Directions (2025.findings-emnlp)

Copied to clipboard

Challenge: Safety-aligned LLMs respond to prompts with compliance or refusal, each corresponding to distinct directions in the model’s activation space.
Approach: They propose an initialization framework that aims to project unseen prompts further along compliance directions.
Outcome: The proposed initialization framework achieves an increased attack success rate and reduced computational overhead, highlighting the fragility of safety-aligned LLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations