Search papers, labs, and topics across Lattice.
3
0
7
12
Robustness against jailbreaks varies over a hundredfold across leading AI models, revealing critical vulnerabilities in AI safety measures.
Open-weight LLMs are systematically vulnerable to prefill attacks, a largely unexplored attack vector that bypasses internal safeguards even in state-of-the-art reasoning models.
Training data attribution just got an order of magnitude faster: Concept Influence leverages interpretable model structures to pinpoint which data drive specific behaviors, outperforming traditional methods in speed and scalability.
