1 code implementation • 29 May 2024 • Zhanhui Zhou, Zhixuan Liu, Jie Liu, Zhichen Dong, Chao Yang, Yu Qiao
In this work, we introduce $\textit{weak-to-strong search}$, framing the alignment of a large language model as a test-time greedy search to maximize the log-likelihood difference between small tuned and untuned models while sampling from the frozen large model.
1 code implementation • 19 Feb 2024 • Zhanhui Zhou, Jie Liu, Zhichen Dong, Jiaheng Liu, Chao Yang, Wanli Ouyang, Yu Qiao
Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans.
1 code implementation • 14 Feb 2024 • Zhichen Dong, Zhanhui Zhou, Chao Yang, Jing Shao, Yu Qiao
Large Language Models (LLMs) are now commonplace in conversation applications.