Influence of Prompts Structure on the Perception and Enhancement of Learning through LLMs in Online Educational Contexts

This research examines how the structure of prompts impacts the perceived depth and accuracy of responses generated by generative Large Language Models (LLMs) in educational settings. It specifically investigates how prompt design influences students’ learning experiences. The study involved an expe...

Descripción completa

Detalles Bibliográficos
Autor: Rodriguez-Donaire, Silvia
Tipo de recurso: capítulo de libro
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/151855
Acceso en línea:https://hdl.handle.net/10609/151855
http://doi.org/10.5772/intechopen.1006481
Access Level:acceso abierto
Palabra clave:generative AI
GenAI
engineering prompts
large language model
LLMs
formative assessment
online higher education
prompt structure
educational environment
students’ perception
learning process
Descripción
Sumario:This research examines how the structure of prompts impacts the perceived depth and accuracy of responses generated by generative Large Language Models (LLMs) in educational settings. It specifically investigates how prompt design influences students’ learning experiences. The study involved an experiment with 183 students enrolled in a mandatory Business Administration course at the Universitat Oberta de Catalunya (UOC). Data from the experiment were analyzed using both qualitative and quantitative methods. The results show that well-structured prompts significantly improve students’ perception of the depth and accuracy of GenAI-generated responses, leading to a more effective learning process. This underscores the crucial role of prompt design in maximizing the educational effectiveness of GenAI. The findings suggest that thoughtful prompt design can enhance educational outcomes, although the study’s limited sample size and context-specific nature may restrict the generalizability of the results. This research contributes to the field by highlighting the importance of prompt structure in harnessing GenAI tools for educational improvement.