Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
Where an LLM stores a fact is rarely where you should erase it: high-precision storage localization picks the optimal unlearning intervention on just 17 of 36 targets, exposing a core blind spot in mechanistic model editing.
Persona skills expose significant privacy risks, with existing defenses failing to adequately protect against attribute disclosure and impersonation across diverse agent architectures.
