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

arXiv:2404.13033v1 Announce Type: new
Abstract: 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 prompt modifications. Yet, the realm of the sample design for downstream fine-tuning, crucial for task-specific LLM adaptation, is largely unexplored. This paper introduces Sample Design Engineering (SDE), a methodical approach to enhancing LLMs' post-tuning performance by refining input, output, and reasoning designs. We conduct a series of in-domain (ID) …

arxiv cs.cl design engineering fine-tuning good llms sample samples study type