Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
Jailbreaking reasoning models turns out to be an effective antidote to RL-induced overconfidence, recovering suppressed pre-alignment entropy to slash black-box calibration error by up to 5脳.
Existing differential privacy methods fail to protect ontological databases against inference attacks, but a new ontology-aware approach closes this gap.
