Generating SQL Queries In The Serbian Language: A Comparative Analysis of Open-Source and Commercial Language Models
Journal of UUNT Informatics and Computer Sciences · 30.06.2026 · 3 (1) · 1
DOI: 10.62907/juuntics260101001s ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of UUNT Informatics and Computer Sciences, online erschienen am 30.06.2026. Verfasst von Slaviša Sovilj und 2 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper investigates the ability of large language models (LLMs) to generate SQL queries based on questions formulated in natural language (Text-to-SQL), with a particular focus on the Serbian language. The aim of the research is to empirically determine the extent to which the query language and task complexity affect the accuracy of the generated SQL code, as well as to identify the dominant sources of errors in the generation process. For this purpose, an experimental environment was developed, comprising a relational database that simulates an employee management system, an evaluation set of 200 tasks divided into four categories according to complexity level, natural-language formulations that the LLM translates into SQL code, and an automated system for executing evaluations in the selected language. The results suggest that the key challenge of Text-to-SQL systems is no longer syntactic validity, but semantic precision and the correct modeling of relationships between entities in the database, while the choice of natural language in which the question is formulated has a negligible impact on the final accuracy.
Zitieren
APA
Sovilj, S., Marković, J., & Dugonjić, I. (2026). Generating SQL Queries In The Serbian Language: A Comparative Analysis of Open-Source and Commercial Language Models. Journal of UUNT Informatics and Computer Sciences, 3(1), 1. https://doi.org/10.62907/juuntics260101001s
Vancouver
Sovilj S, Marković J, Dugonjić I. Generating SQL Queries In The Serbian Language: A Comparative Analysis of Open-Source and Commercial Language Models. Journal of UUNT Informatics and Computer Sciences. 2026;3(1):1. doi:10.62907/juuntics260101001s
BibTeX
@article{Sovilj2026,
author = {Sovilj, Slaviša and Marković, Jovo and Dugonjić, Igor},
title = {Generating SQL Queries In The Serbian Language: A Comparative Analysis of Open-Source and Commercial Language Models},
journal = {Journal of UUNT Informatics and Computer Sciences},
year = {2026},
volume = {3},
number = {1},
pages = {1},
doi = {10.62907/juuntics260101001s}
}
EUVIMED