Paper recorded by Signals 4 on 2026-11-02 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03
Category: cs.CL · 自然语言处理 · first seen 2026-11-03
Whether an aligned language model refuses depends in part on which words a prompt contains, regardless of whether those words carry the request's meaning. Harm words shift the hidden state at the generation boundary along a component shared across prompts and words, which crossed differencing extracts as a single direction. In eight models, writing along this direction raises and lowers refusal mo