together 11 Prompting techniques 13 General prompting / zero shot 13 One-shot & few-shot 15 System, contextual and role prompting 18 System prompting 19 Role prompting 21 Contextual prompting 23 Table contents Step-back prompting 25 Chain of Thought (CoT) 29 Self-consistency 32 Tree of Thoughts (ToT) 36 ReAct (reason & act) 37 Automatic Prompt Engineering 40 Code prompting 42 Prompts for writing Prompts for translating code 46 Prompts for debugging and reviewing code 48 What about multimodal prompting? 54 Best Practices 54 Provide examples 54 Design with simplicity 55 Be specific about the output

million的网页、大小40GB的文本。 图：GPT-2通过调整原模型和采用多任务方式来让AI更贴近“通才” 水平 GPT的发展 37 资料来源：《 Language Models are Few-Shot Learners》论文 • 预训练加微调范式中，可能在这种范式下实现的 泛化可能很差，因为该模型过于特定于训练分布， 并且在其之外无法很好地泛化。 • 微调模型在特定基准上的性能，即使名义上是人 现了强大性能 ✓ GPT-3是一个具有1750亿个参数的自回归语言模型，比之前的任何非稀疏语言模型多10倍。对于所有任务（在few-shot设置下测试其 性能），GPT-3都是在没有任何梯度更新或微调的情况下应用的，仅通过与模型的文本交互来指定任务和few-shot演示。 ✓ GPT-3在许多NLP数据集上都有很强的性能（包括翻译、问题解答和完形填空任务），以及一些需要动态推理或领域适应的任务（如解 GPT-3可以生成新闻文章样本（已很难将其与人类撰写的文章区分开来）。 图：GPT-3相关研究显示，few-shot(少量样本）的综 合表现是在无监督模式下最优的 图：GPT-3的模型参数在GPT-2的基础上增加110多倍 资料来源：《 Language Models are Few-Shot Learners》 GPT的发展 39 资料来源：《Training language models

official Tensorflow Hub repository8. Similarly models like GPT-3, T5, etc. have the capability to be few-shot learners. This means that they can be shown a few example inputs and outputs to solve a new task perform sentiment detection by showing it a few examples of the task. Figure 6-7: An example of few-shot learning with a large language model. One of the prominent deployment of such models is the GitHub’s achieve higher quality models with scant labeled data. In fact very large models like GPT-3 are few-shot learners, in that they can be shown a couple of examples of the task to be solved, and they can

2019  #13.4 Alireza Heidari, Joshua McGrath, Ihab F. Ilyas, Theodoros Rekatsinas: HoloDetect: Few-Shot Learning for Error Detection. SIGMOD 2019  #13.5 Theodoros Rekatsinas, Xu Chu, Ihab F. Ilyas,

this growth sustainable with efficient deep learning. 5 Brown, Tom B., et al. "Language models are few-shot learners." arXiv preprint arXiv:2005.14165 (2020). 4 Devlin, Jacob, et al. "Bert: Pre-training

LLaMA3 70B Instruct, might not strictly adhere to the format constraints typically specified in the few-shot setting. Consequently, this can lead to underestimation of certain models in our evaluation framework

Saliency-Aware Topic Modeling.” AAAI (2021). [55] Brown, Tom B. et al. “Language Models are Few-Shot Learners.” ArXiv abs/2005.14165 (2020): n. pag. [56] Radford, Alec, Jeff Wu, Rewon Child, David that matters: Small language models are also few-shot learners.” arXiv preprint arXiv:2009.07118 (2020). [11] Wang, Sinong, et al. “Entailment as few-shot learner.” arXiv preprint arXiv:2104.14690 (2021)

conventions • supports loading values from environment variables out of the box • supports for prompting of custom values • is fully nestable and composable • works the same on Python 2 and 3 • supports Arguments can do less than options. The following features are only available for options: • automatic prompting for missing input • act as flags (boolean or otherwise) • option values can be pulled from environment this message and exit. 12 Chapter 1. Documentation Click Documentation, Release 1.2.dev0 1.4.8 Prompting Sometimes you want parameters that can either be provided from the command line or if not, you

conventions • supports loading values from environment variables out of the box • supports for prompting of custom values • is fully nestable and composable • works the same in Python 2 and 3 • supports Arguments can do less than options. The following features are only available for options: • automatic prompting for missing input • act as flags (boolean or otherwise) • option values can be pulled from environment Usage: digest [OPTIONS] Options: --hash-type [md5|sha1] --help Show this message and exit. 1.5.9 Prompting In some cases, you want parameters that can be provided from the command line, but if not provided

conventions • supports loading values from environment variables out of the box • supports for prompting of custom values • is fully nestable and composable • works the same in Python 2 and 3 • supports Arguments can do less than options. The following features are only available for options: • automatic prompting for missing input • act as flags (boolean or otherwise) • option values can be pulled from environment Usage: digest [OPTIONS] Options: --hash-type [md5|sha1] --help Show this message and exit. 1.5.9 Prompting In some cases, you want parameters that can be provided from the command line, but if not provided