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 Measurement of Perceived Quality in Conversational Systems (Chatbots)(Springer Nature, 2025-03-25) Hernández-Pupo, Luis Gabriel; Yzquierdo-Herrera, Raykenler; Alvarado-Acuña, Luis Segundo; Piñero-Pérez, Pedro Yobanis; Pérez-Pupo, Iliana; Bello-Pérez, RafaelThe increase in the number of conversational systems (chatbots) applied to different scenarios in society is notable. However, the development of metrics and evaluation methods for chatbots still remains an open line of research. The aim is to create evaluation methods that are less and less invasive and that do not reduce the participation of users or other human agents. In this work, in the methods section, a systematic review is carried out on different evaluation methods for chatbots. Then, in the same section, new metrics for the evaluation of conversations with chatbots inspired by the neutrosophic theory are presented. In the results section, the validation of the proposed model is carried out. The applicability of the model is evaluated and the proposal is subjected to expert triangulation methods. In the work, it is possible to demonstrate that the application of neutrosophic logic can contribute to achieving a more natural response from chatbots. This effect can be useful to mitigate the presence of false responses or hallucinations.