Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/152145
Title: AVALUACIÓ DELS LLMs EN FUNCIÓ DEL NIVELL EDUCATIU I EL CONTEXT DE LES PREGUNTES
Author: Capell Sala, Marc
Director: Sánchez Castaño, Friman
Tutor: Moyà Alcover, Gabriel
Abstract: Large Language Models (LLMs) have gained significant popularity in the recent years, and it is increasingly evident that they will become a common tool in various areas of daily life. However, students have embraced this new technology enthusiastically, often without a clear understanding of how to use it effectively. This project evaluates the results produced by LLMs at different educational levels (primary school, secondary school, and university entrance exams) and across various subjects (language, science, mathematics, etc.) with the goal of providing a framework to understand where LLMs can be most helpful. The results indicate that LLMs perform well in language-related tasks but face significant challenges when solving problems in physics and mathematics, where small details have a considerable impact on the final result. Lastly, it was observed that multimodal functionalities, such as image analysis, still do not deliver entirely satisfactory outcomes.
Keywords: Machine learning
Large Language Models (LLMs)
Education
Document type: info:eu-repo/semantics/bachelorThesis
Issue Date: 2025
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
Memoria_TFG_Marc_Capell.pdf764,27 kBAdobe PDFThumbnail
View/Open
Presentacio_TFG_Marc_Capell.pdf532,79 kBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.