safety-at-one-shot-lm-repair

【数据与研究】Recover safety alignment in fine-tuned LLMs using only a single safety example, without sacrificing utility. Leverages low-rank structure of safety gradients to enable minimal-cost correction even when models have been compromised by extensive harmful training data.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准