The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913707867504640 |
|---|---|
| author | Schulhoff, Sander Ilie, Michael Balepur, Nishant Kahadze, Konstantine Liu, Amanda Si, Chenglei Li, Yinheng Gupta, Aayush Han, HyoJung Schulhoff, Sevien Dulepet, Pranav Sandeep Vidyadhara, Saurav Ki, Dayeon Agrawal, Sweta Pham, Chau Kroiz, Gerson Li, Feileen Tao, Hudson Srivastava, Ashay Da Costa, Hevander Gupta, Saloni Rogers, Megan L. Goncearenco, Inna Sarli, Giuseppe Galynker, Igor Peskoff, Denis Carpuat, Marine White, Jules Anadkat, Shyamal Hoyle, Alexander Resnik, Philip |
| author_facet | Schulhoff, Sander Ilie, Michael Balepur, Nishant Kahadze, Konstantine Liu, Amanda Si, Chenglei Li, Yinheng Gupta, Aayush Han, HyoJung Schulhoff, Sevien Dulepet, Pranav Sandeep Vidyadhara, Saurav Ki, Dayeon Agrawal, Sweta Pham, Chau Kroiz, Gerson Li, Feileen Tao, Hudson Srivastava, Ashay Da Costa, Hevander Gupta, Saloni Rogers, Megan L. Goncearenco, Inna Sarli, Giuseppe Galynker, Igor Peskoff, Denis Carpuat, Marine White, Jules Anadkat, Shyamal Hoyle, Alexander Resnik, Philip |
| contents | Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these systems through the use of prompting and prompt engineering. Although prompt engineering is a widely adopted and extensively researched area, it suffers from conflicting terminology and a fragmented ontological understanding of what constitutes an effective prompt due to its relatively recent emergence. We establish a structured understanding of prompt engineering by assembling a taxonomy of prompting techniques and analyzing their applications. We present a detailed vocabulary of 33 vocabulary terms, a taxonomy of 58 LLM prompting techniques, and 40 techniques for other modalities. Additionally, we provide best practices and guidelines for prompt engineering, including advice for prompting state-of-the-art (SOTA) LLMs such as ChatGPT. We further present a meta-analysis of the entire literature on natural language prefix-prompting. As a culmination of these efforts, this paper presents the most comprehensive survey on prompt engineering to date. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06608 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Prompt Report: A Systematic Survey of Prompt Engineering Techniques Schulhoff, Sander Ilie, Michael Balepur, Nishant Kahadze, Konstantine Liu, Amanda Si, Chenglei Li, Yinheng Gupta, Aayush Han, HyoJung Schulhoff, Sevien Dulepet, Pranav Sandeep Vidyadhara, Saurav Ki, Dayeon Agrawal, Sweta Pham, Chau Kroiz, Gerson Li, Feileen Tao, Hudson Srivastava, Ashay Da Costa, Hevander Gupta, Saloni Rogers, Megan L. Goncearenco, Inna Sarli, Giuseppe Galynker, Igor Peskoff, Denis Carpuat, Marine White, Jules Anadkat, Shyamal Hoyle, Alexander Resnik, Philip Computation and Language Artificial Intelligence Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these systems through the use of prompting and prompt engineering. Although prompt engineering is a widely adopted and extensively researched area, it suffers from conflicting terminology and a fragmented ontological understanding of what constitutes an effective prompt due to its relatively recent emergence. We establish a structured understanding of prompt engineering by assembling a taxonomy of prompting techniques and analyzing their applications. We present a detailed vocabulary of 33 vocabulary terms, a taxonomy of 58 LLM prompting techniques, and 40 techniques for other modalities. Additionally, we provide best practices and guidelines for prompt engineering, including advice for prompting state-of-the-art (SOTA) LLMs such as ChatGPT. We further present a meta-analysis of the entire literature on natural language prefix-prompting. As a culmination of these efforts, this paper presents the most comprehensive survey on prompt engineering to date. |
| title | The Prompt Report: A Systematic Survey of Prompt Engineering Techniques |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.06608 |