Papers
arxiv:2406.06608

The Prompt Report: A Systematic Survey of Prompting Techniques

Published on Jun 6
· Submitted by akhaliq on Jun 12
#2 Paper of the day

Abstract

Generative Artificial Intelligence (GenAI) systems are being increasingly deployed across all parts of industry and research settings. Developers and end users interact with these systems through the use of prompting or prompt engineering. While prompting is a widespread and highly researched concept, there exists conflicting terminology and a poor ontological understanding of what constitutes a prompt due to the area's nascency. This paper establishes a structured understanding of prompts, by assembling a taxonomy of prompting techniques and analyzing their use. We present a comprehensive vocabulary of 33 vocabulary terms, a taxonomy of 58 text-only prompting techniques, and 40 techniques for other modalities. We further present a meta-analysis of the entire literature on natural language prefix-prompting.

Community

This was the most practical survey paper Ive ever read. Excellent work, you should all be very proud of yourselves.

·
Paper author

Thank you! What could we improve on in the next version?

"The Prompt Report: A Systematic Survey of Prompting Techniques" is an impressive and thorough examination of prompting techniques in AI. The comprehensive taxonomy and detailed analysis of both textual and multimodal prompts provide valuable insights. This report is an excellent resource for researchers and practitioners seeking to understand and apply effective prompting strategies in various AI applications. It also addresses critical aspects like safety and evaluation, making it a significant contribution to the field.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2406.06608 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2406.06608 in a Space README.md to link it from this page.

Collections including this paper 25