Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate human-led prompting followed, with some progress achieved. In particular, subsequent work demonstrates automation can outperform fine-tuning in certain K-shot learning scenarios. In this paper, we revisit techniques for automated prompting on six different downstream tasks and a larger range of K-shot learning settings. We find that automated prompting does not consistently outperform simple manual prompts. Our work suggests that, in addition to fine-tuning, manual prompts should be used as a baseline in this line of research.

翻译：当前文献表明，大型语言模型（LLMs）是优秀的小样本学习器，而提示（prompting）在小样本学习设置下显著提升了它们在多种下游任务上的表现。随后，人们尝试将人工驱动的提示自动化，并取得了一定进展。特别是，后续研究显示，在某些K样本学习场景下，自动化方法可以超越微调（fine-tuning）。在本文中，我们针对六种不同的下游任务以及更广泛的K样本学习设置，重新审视了自动提示技术。我们发现，自动提示并不总是优于简单的人工提示。我们的研究表明，除微调外，人工提示应作为该研究方向的一类基线。