作者位次 #8/8NeurIPS 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Wonjun Lee · Kyungsik Yang · Gaeun Ji · Vaidehi Patil · Haon Park · Bumsub Ham · Mohit Bansal · Suhyun Kim