Publication:
Autonomous Prompt Engineering in Large Language Models

Simple item page
dc.contributor.authorValogianni, Konstantina
dc.contributor.authorKepel, Daan
dc.contributor.funderOpenAI Researcher Access Program
dc.contributor.rorhttps://ror.org/02jjdwm75
dc.date.accessioned2024-11-08T14:47:07Z
dc.date.available2024-11-08T14:47:07Z
dc.date.issued2024-06-25
dc.description.abstractPrompt engineering is a crucial yet challenging task for optimizing the performance of large language models (LLMs) on customized tasks. This pioneering research introduces the Automatic Prompt Engineering Toolbox (APET), which enables GPT-4 to autonomously apply prompt engineering techniques. By leveraging sophisticated strategies such as Expert Prompting, Chain of Thought, and Tree of Thoughts, APET empowers GPT-4 to dynamically optimize prompts, resulting in substantial improvements in tasks like Word Sorting (4.4% increase) and Geometric Shapes (6.8% increase). Despite encountering challenges in complex tasks such as Checkmate in One (-14.8%), these findings demonstrate the transformative potential of APET in automating complex prompt optimization processes without the use of external data. Overall, this research represents a significant leap in AI development, presenting a robust framework for future innovations in autonomous AI systems and highlighting the ability of GPT-4 to bring prompt engineering theory to practice. It establishes a foundation for enhancing performance in complex task performance and broadening the practical applications of these techniques in real-world scenarios.
dc.description.peerreviewedno
dc.description.statusPublished
dc.formatapplication/pdf
dc.identifier.citationKepel, D., & Valogianni, K. (2024). Autonomous Prompt Engineering in Large Language Models. arXiv preprint arXiv:2407.11000. https://doi.org/10.48550/arXiv.2407.11000
dc.identifier.doihttps://doi.org/10.48550/arXiv.2407.11000
dc.identifier.issnNO
dc.identifier.officialurlhttps://arxiv.org/
dc.identifier.urihttps://hdl.handle.net/20.500.14417/3324
dc.journal.titlearXiv
dc.language.isoen
dc.page.final38
dc.page.initial1
dc.page.total38
dc.publisherCornell University
dc.relation.departmentInformation Systems & Technology
dc.relation.entityIE University
dc.relation.schoolIE Business School
dc.rightsAttribution-Non commercial-ShareaAlike 4.0 International
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/4.0/deed.en
dc.subject.keywordLanguage Models
dc.titleAutonomous Prompt Engineering in Large Language Models
dc.typeinfo:eu-repo/semantics/article
dc.version.typeinfo:eu-repo/semantics/publishedVersion
dspace.entity.typePublication
relation.isAuthorOfPublication176a05d2-7442-4e6e-a6da-dcf2f9063787
relation.isAuthorOfPublication.latestForDiscovery176a05d2-7442-4e6e-a6da-dcf2f9063787
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Autonomous Prompt Engineering in Large Language Models.pdf
Size:
462.08 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.83 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Research Articles