1
LLMs Encode Harmfulness and Refusal Separately
最新研究发现：LLM能分离编码“有害性”与“拒绝行为”，揭示安全机制新维度。
arXiv:2507.11878v5 Announce Type: replace Abstract: LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond j…
最新研究发现：LLM能分离编码“有害性”与“拒绝行为”，揭示安全机制新维度。
arXiv:2507.11878v5 Announce Type: replace Abstract: LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond j…