Prompt Engineering Guide
πŸ˜ƒ Basics
πŸ’Ό Applications
πŸ§™β€β™‚οΈ Intermediate
🧠 Advanced
Special Topics
🌱 New Techniques
πŸ€– Agents
βš–οΈ Reliability
πŸ–ΌοΈ Image Prompting
πŸ”“ Prompt Hacking
πŸ”¨ Tooling
πŸ’ͺ Prompt Tuning
πŸ—‚οΈ RAG
🎲 Miscellaneous
Models
πŸ”§ Models
Resources
πŸ“™ Vocabulary Resource
πŸ“š Bibliography
πŸ“¦ Prompted Products
πŸ›Έ Additional Resources
πŸ”₯ Hot Topics
✨ Credits
πŸ§™β€β™‚οΈ Intermediate🟒 Introduction

Introduction

🟒 This article is rated easy
Reading Time: 1 minute
Last updated on August 7, 2024

Sander Schulhoff

Takeaways
  • Understand what a prompting technique is
  • Understand the contents of the Intermediate section

You have made it through the beginning stages of Prompt Engineering! Now you can dive into some intermediate techniques which can really take your prompting to the next level.

Here, you are going to shift your focus from the tasks that GenAI can solve, onto the prompting techniques themselves. According to The Prompt Report, "a prompting technique is a blueprint that describes how to structure a prompt, prompts, or dynamic sequencing of multiple prompts. A prompting technique may incorporate conditional or branching logic, parallelism, or other architectural considerations spanning multiple prompt". In the coming lessons, we will focus on more technical aspects of prompting such as prompt structure and design.

This module will expose you to moderately complex, research-based prompt engineering techniques. You'll learn how to implement these techniques to improve the performance of your GenAI applications. Some topics we will explore are Chain-of-Thought, Self-Consistency, and Generated knowledge. We will also revisit a technique we have already touched on, Role Prompting, and expand on its use. Along the way, you will also learn more about where prompting LLMs (Large Language Models) can fail.

By the end of this module, you will have a fundamental understanding of many of the world's most used prompting techniques and be able to apply them to a myriad of tasks.

Sander Schulhoff

Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.

🟒 Chain-of-Thought Prompting

🟒 LLM Settings

🟦 Generated Knowledge

🟦 Least-to-Most Prompting

🟦 Dealing With Long Form Content

🟒 OpenAI Playground

🟦 Revisiting Roles

🟦 Self-Consistency

🟒 What's in a Prompt?

🟒 Zero-Shot Chain-of-Thought

Footnotes

  1. Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., Dulepet, P. S., Vidyadhara, S., Ki, D., Agrawal, S., Pham, C., Kroiz, G., Li, F., Tao, H., Srivastava, A., … Resnik, P. (2024). The Prompt Report: A Systematic Survey of Prompting Techniques. https://arxiv.org/abs/2406.06608 ↩ ↩2