Poster · Atlanta

Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge

Name: Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Start: 2026-12-09T10:00:00-05:00
End: 2026-12-09T13:00:00-05:00
Location: Hall C1, Georgia World Congress Center

When: Wed 9 Dec 2026, 10:00–13:00 EST
Where: Hall C1, Georgia World Congress Center
Session: Atlanta Poster Session 1
Authors: Wonjun Lee, Kyungsik Yang, Gaeun Ji, Vaidehi Patil, Haon Park, Bumsub Ham, Mohit Bansal, Suhyun Kim
Organisations: University of North Carolina at Chapel Hill, Kyung Hee University, AIM Intelligence, Yonsei University
QRS classification: Language models, Safety, fairness and privacy

Open in schedule Official page