Back to papers
July 13, 2026cs.LGcs.CL

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang
Read on arXivDownload PDF
Categories

cs.LG, cs.CL