Optimization of Large Language Models (LLMs) through Prompt Engineering

• Autores: Paz Fernández, Crishtian Brenon, Diaz Sifuentes, Sergio Helí, Torres Villanueva, Marcelino
• Formato: artículo
• Fecha de Publicación: 2025
• Institución: Universidad La Salle
• Repositorio: Revistas - Universidad La Salle
• Lenguaje: español
• OAI Identifier: oai:ojs.revistas.ulasalle.edu.pe:article/212
• Enlace del recurso: https://revistas.ulasalle.edu.pe/innosoft/article/view/212; https://doi.org/10.48168/innosoft.s24.a212; https://purl.org/42411/s24/a212; https://n2t.net/ark:/42411/s24/a212
• Nivel de acceso: acceso abierto
• Materia: Few-shot learning; generative models; LLMs; prompt engineering; zero-shot learning; modelos generativos

This article explored the impact of prompt engineering on optimizing the performance of large language models (LLMs) such as GPT and BERT. Prompt engineering was introduced as an innovative approach that involved designing specific instructions to guide the models' responses, enhancing their accuracy and relevance without modifying their internal parameters. The study evaluated methodologies for constructing effective prompts, compared different strategies such as few-shot and zero-shot learning, and analyzed practical cases in areas like text generation, question answering, and sentiment analysis. The results demonstrated that a strategic design of prompts could significantly improve response quality, reduce errors, and expand the range of LLM applications.