Adversarial Contrastive Decoding: Boosting Safety Alignment of Large Language Models Via Opposite Prompt Optimization Z. G. Zhao, Xiaoyun Zhang,Kaidi Xu,Xing Jun Hu,Rui Zhang,Zidong Du,Qi Guo,Tianshi ChenarXiv (Cornell University)（2024）引用 0|浏览4AI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
