git-disl/Lisa

This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)

⭐ 29 ⑂ 0 Python Apache-2.0 · 2024-09-11推送

https://arxiv.org/abs/2405.18641

attack fine-tuning finetuning llm emergent harmful malicious misalignment

29

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

2024-09-11

最近推送

原文中文

暂无 README