Autonomous Prompt Engineering in Large Language Models

Prompt 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 le...

Descripción completa

Detalles Bibliográficos
Autores: Valogianni, Konstantina, Kepel, Daan
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:IE
Repositorio:Repositorio IE
OAI Identifier:oai:repositorio.ie.edu:20.500.14417/3324
Acceso en línea:https://doi.org/10.48550/arXiv.2407.11000
https://hdl.handle.net/20.500.14417/3324
https://arxiv.org/
Access Level:acceso abierto
Palabra clave:Language Models
12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
ODS 9 - Industria, innovación e infraestructura
Descripción
Sumario:Prompt 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.