CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment

no code implementations • 25 Oct 2023 • Jixiang Hong, Quan Tu, Changyu Chen, Xing Gao, Ji Zhang, Rui Yan

With in-context learning (ICL) as the core of the cycle, the black-box models are able to rank the model-generated responses guided by human-craft instruction and demonstrations about their preferences.

In-Context Learning Instruction Following +2