重新审视自动化提示：我们真的做得更好吗？
Revisiting Automated Prompting: Are We Actually Doing Better?
AI总结：
本文重新审视自动化提示技术，发现其在多个任务和K样本设置下并不始终优于手动提示，建议将手动提示作为基线。
摘要：
当前文献表明，大型语言模型（LLMs）是出色的少样本学习者，提示显著提升了它们在少样本学习设置中一系列下游任务上的表现。随后，人们尝试自动化人工引导的提示，并取得了一些进展。特别是，后续工作表明，在某些K样本学习场景中，自动化可以超越微调。在本文中，我们重新审视了六种不同下游任务及更广泛的K样本学习设置下的自动化提示技术。我们发现，自动化提示并不始终优于简单的手动提示。我们的工作表明，除了微调之外，手动提示也应作为该研究方向的一个基线。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
