Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs

Biyang Guo, He Wang, Wenyilin Xiao +4

In the burgeoning field of Large Language Models (LLMs) like ChatGPT and LLaMA, Prompt Engineering (PE) is renowned for boosting zero-shot or in-context learning (ICL) through prom…