Bach. Enrique Vílchez Lizano
Labor:
Es estudiante:
Si
Programa en que estudia:
Programa de Posgrado en Computación e Informática (PPCI)
Proyectos
Uso de la inteligencia artificial como apoyo a la lectura compartida infantil
Número de proyecto:
834-C5-189
De 03/Mar/2025 hasta 29/Feb/2028
Publicaciones
An Empirical Study of LLM-Based Source Code Quality Assessment under ISO/IEC 5055:2021
May
2026
Descripción:
Nowadays, many software companies are required to meet high quality standards in the development of their applications. Rather than replacing traditional SAST tools based on fixed rules, approaches such as GemCA leverage a Large Language Model (LLM) to perform semantic reasoning over code in relation to the ISO/IEC 5055:2021 standard, providing a complementary decision-support mechanism for early-stage quality assessment. This paper presents GemCA and reports an empirical analysis evaluating its accuracy on a dataset of known code weaknesses. The goal is to examine the framework’s ability to apply the criteria defined by the ISO/IEC 5055:2021 standard. Results show that GemCA achieves an average accuracy of 81% across 15 repetitions, with significantly higher performance in C# than PHP. However, accuracy varies substantially across weakness categories (p = 0.0000), indicating sensitivity to CWE type and programming language. These findings highlight both the potential and the current limitations of LLM-based analysis for ISO/IEC 5055:2021 compliance.
Tipo de publicación: Conference Paper
Publicado en: Anais do XXIX Congresso Ibero-Americano em Engenharia de Software (CIbSE 2026)
A systematic mapping on the use of artificial intelligence for children’s reading development
Nov
2025
Descripción:Children’s exposure to reading experiences and books can have a positive impact on language development, vocabulary acquisition, and even academic success. Recently, artificial intelligence (AI) has emerged as a tool for assisting story writing and learning in general. However, a systematic study exploring the use of AI in the context of children’s reading development is lacking. Hence, this study analyzes how AI techniques have been used to develop children’s reading, their evaluation methods, benefits, and target child population. A systematic literature mapping of 37 primary studies was performed, where we identified 13 AI techniques, 14 uses, 8 evaluation methods, and 17 benefits. Our results reveal a trend in the use of transformer models, with story writing and question generation being their main uses. Results also point to computable metrics and expert evaluations as the main evaluation methods. AI techniques benefit children’s cognitive and skill development, and improve content quality and personalization.
Tipo de publicación: Conference Paper
Publicado en: 2025 IEEE 43rd Central America and Panama Convention (CONCAPAN XLIII)
Automated Personalization of Children's Storybook Images: A Case Study
Abr
2026
Tipo de publicación: Conference Paper
Publicado en: Recent Trends and Challenges in Information Systems and Technologies