Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations 文章
ArXiv CS.AI2026-05-28NEWSen作者: Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta, Denis Kleyko, Mauro Conti, Matteo Zavatteri, Roberto Confalonieri