saffron

Saffron-1：面向LLM安全保证的推理扩展 📖 论文 🛠️ 依赖 代码在以下依赖环境中测试通过： Python 3.12.3 CUDA 12.2 typingextensions==4.14.0 numpy==2.2.6 torch==2.5.1 huggingfacehub==0.30.2 accelerate==1.1.1 datasets==3.1.0 evaluate==0.4.3 transformers==4.45.2 peft==0.15.0 deepspeed==0.16.7 🚀 用法 请参见 saffron.py。更多描述即将推出... 📊 结果...

Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance

Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently, inference scaling has significantly advanced LLM reasoning...