Alvarado-Acuña, Luis Segundo
Cargando...
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Alvarado-Acuña
Nombres
Luis Segundo
Nombre
Dirección de correo electrónico
lualvar@ucn.cl
Fecha de nacimiento
2 resultados
Resultados de la búsqueda
Mostrando 1 - 2 de 2
Publicación Characterization of SLM Conversational Systems Models, Overview(Springer Nature, 2025-03-25) Vasconcelo-Mir, Yuniesky Orlando; Pérez-Pupo, Iliana; Yzquierdo-Herrera, Raykenler; Piñero-Pérez, Pedro Yobanis; Alvarado-Acuña, Luis Segundo; Bello-Pérez, RafaelThe development of Generative Artificial Intelligence is revolutionizing human–machine interaction models. In this context, large language models (LLMs) have emerged as tools capable of learning complex patterns. However, many of these technologies are highly resource intensive. An alternative to these complex models is the advent of Small Language Models (SLMs). These smaller models process fewer parameters but achieve acceptable performance in their responses, striking a balance between cost and quality. This study characterizes different SLMs to facilitate decision-making in their implementation. In the methods section, a systematic review is conducted, serving as a guide for researchers and professionals seeking to select the most suitable SLM for their specific needs. An analysis of the efficiency of these models contributes to the application of Artificial Intelligence techniques from a sustainability perspective. The results section presents a comparison of various SLMs available on the Ollama platform. The models compared include Qwen2.5, Phi3.5, Mistral-small, Llama3.1, and Gemma2. A comparative analysis evaluates these models based on their efficiency and effectiveness in terms of computational resources and the human effort required to develop task-specific conversational systems. The study demonstrates the feasibility of using these smaller models in various decision-making environments.Publicación Ecosystem IADESCom for Conversational System Construction(Springer Nature, 2025-03-25) Pérez-Pupo, Iliana; Piñero-Pérez, Pedro Yobanis; Vasconcelo-Mir, Yuniesky Orlando; Yzquierdo-Herrera, Raykenler; Alvarado-Acuña, Luis Segundo; Piñero-Ramírez, Pedro E.Conversational systems are rapidly changing and modifying the ways in which humans interact with machines. A basic classification divides these systems into two fundamental groups: classical systems based on NLU techniques and systems based on LLM models. In this context, the number of application scenarios for these systems and their impact on business efficiency is increasing. In this sense, opportunities for applications in reservation management, information retrieval and the execution of actions in information systems are identified. In this sense, it was identified that the construction of the training bases for these systems is costly in time and effort. In the methods section of this work, the IADESCom software ecosystem is presented. This ecosystem is made up of a set of COTS components that allow the application of conversational systems in different scenarios. In the results section, the different components are validated and the applicability of the ecosystem is demonstrated. Finally, the conclusions and future work are presented.