将提示工程视为研究大模型的科学方法，而非神秘操作。
Prompting as Scientific Inquiry
- 把大模型看作需通过语言交互研究的复杂有机体
- 提示是探测模型行为的原生界面，非临时权宜之计
- 适合对模型机制探索感兴趣的科研人员
提示是研究和控制大语言模型的主要方法，也是最强大的手段之一：几乎所有大模型的重要能力——如少样本学习、思维链、宪法式AI——最初都是通过提示解锁的。然而，提示常被当作炼金术而受到轻视，未被视为科学。我们主张这是分类错误。若将大模型视为一种训练而非编程而成的复杂且不透明的生物体，则提示不是权宜之计，而是行为科学。机械可解释性研究神经底层结构，提示则在模型的自然接口——语言层面进行探测。我们认为，提示并非劣等，反而是大模型科学的关键组成部分。
原文摘要 · Abstract (English)
Prompting is the primary method by which we study and control large language models. It is also one of the most powerful: nearly every major capability attributed to LLMs-few-shot learning, chain-of-thought, constitutional AI-was first unlocked through prompting. Yet prompting is rarely treated as science and is frequently frowned upon as alchemy. We argue that this is a category error. If we treat LLMs as a new kind of complex and opaque organism that is trained rather than programmed, then prompting is not a workaround: it is behavioral science. Mechanistic interpretability peers into the neural substrate, prompting probes the model in its native interface: language. We contend that prompting is not inferior, but rather a key component in the science of LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。