Saved in:
Bibliographic Details
Main Authors: Pozo, Micaela Fuel, Saltos, Andrea Guatumillo, Llumiquinga, Yeseña Tipan, Aguirre, Kelly Lascano, Jara, Marilyn Castillo, Mejia-Escobar, Christian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.02653
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916987164164096
author Pozo, Micaela Fuel
Saltos, Andrea Guatumillo
Llumiquinga, Yeseña Tipan
Aguirre, Kelly Lascano
Jara, Marilyn Castillo
Mejia-Escobar, Christian
author_facet Pozo, Micaela Fuel
Saltos, Andrea Guatumillo
Llumiquinga, Yeseña Tipan
Aguirre, Kelly Lascano
Jara, Marilyn Castillo
Mejia-Escobar, Christian
contents This study presents the development of Geolog-IA, a novel conversational system based on artificial intelligence that responds naturally to questions about geology theses from the Central University of Ecuador. Our proposal uses the Llama 3.1 and Gemini 2.5 language models, which are complemented by a Retrieval Augmented Generation (RAG) architecture and an SQLite database. This strategy allows us to overcome problems such as hallucinations and outdated knowledge. The evaluation of Geolog-IA's performance with the BLEU metric reaches an average of 0.87, indicating high consistency and accuracy in the responses generated. The system offers an intuitive, web-based interface that facilitates interaction and information retrieval for directors, teachers, students, and administrative staff at the institution. This tool can be a key support in education, training, and research and establishes a basis for future applications in other disciplines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02653
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Geolog-IA: Conversational System for Academic Theses
Pozo, Micaela Fuel
Saltos, Andrea Guatumillo
Llumiquinga, Yeseña Tipan
Aguirre, Kelly Lascano
Jara, Marilyn Castillo
Mejia-Escobar, Christian
Artificial Intelligence
Information Retrieval
This study presents the development of Geolog-IA, a novel conversational system based on artificial intelligence that responds naturally to questions about geology theses from the Central University of Ecuador. Our proposal uses the Llama 3.1 and Gemini 2.5 language models, which are complemented by a Retrieval Augmented Generation (RAG) architecture and an SQLite database. This strategy allows us to overcome problems such as hallucinations and outdated knowledge. The evaluation of Geolog-IA's performance with the BLEU metric reaches an average of 0.87, indicating high consistency and accuracy in the responses generated. The system offers an intuitive, web-based interface that facilitates interaction and information retrieval for directors, teachers, students, and administrative staff at the institution. This tool can be a key support in education, training, and research and establishes a basis for future applications in other disciplines.
title Geolog-IA: Conversational System for Academic Theses
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2510.02653