🟢 Introduction

Reading Time: 1 minute

Last updated on September 27, 2024

Now, let’s dive into advanced prompting techniques. Sander Schulhoff, the founder of Learn Prompting, published The Prompt Report, the most comprehensive survey on prompting to date. In this report, he categorized prompting techniques into six main classifications:

While many techniques overlap across these classifications, each one generally has a primary category that it fits best. Read on to explore these different classes of techniques and how they are used.

Note

These sections are currently being frequently updated.

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.

Footnotes

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 ↩

Edit this page

Word count: 0

🟢 Introduction

Sander Schulhoff

Decomposition

Ensembling

Few-Shot

Self-Criticism

Thought Generation

Zero-Shot

Footnotes

🟢 OpenAI Playground

🟢 Introduction

Get AI Certified by Learn Prompting