Approaches to Lightweight Text-to-SQL Implementation Based on sLLM 


Vol. 50,  No. 8, pp. 1183-1191, Aug.  2025
10.7840/kics.2025.50.8.1183


PDF Full-Text
  Abstract

This study proposes a lightweight Text-to-SQL implementation based on sLLM (smaller Large Language Model) to solve the high cost and security issues of existing LLM (Large Language Model) based Text-to-SQL models. To this end, we implemented a Text-to-SQL model using DAIL-SQL[1] and Llama3-8B and evaluated its performance using Spider dataset[2]. In this study, we secure the shortcomings of the existing Few-shot Learning method and propose improvement measures such as fine-tuning, knowledge distillation, and selection of similar queries through RAG to improve the performance of sLLM-based Text-to-SQL. By resolving the security vulnerabilities of existing LLM-based Text-to-SQL and presenting an efficient way to implement sLLM-based Text-to-SQL, we expect to expand the utilization of Text-to-SQL in various industries.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Im and S. Yoon, "Approaches to Lightweight Text-to-SQL Implementation Based on sLLM," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 8, pp. 1183-1191, 2025. DOI: 10.7840/kics.2025.50.8.1183.

[ACM Style]

Jae-young Im and Soo-Yeon Yoon. 2025. Approaches to Lightweight Text-to-SQL Implementation Based on sLLM. The Journal of Korean Institute of Communications and Information Sciences, 50, 8, (2025), 1183-1191. DOI: 10.7840/kics.2025.50.8.1183.

[KICS Style]

Jae-young Im and Soo-Yeon Yoon, "Approaches to Lightweight Text-to-SQL Implementation Based on sLLM," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 8, pp. 1183-1191, 8. 2025. (https://doi.org/10.7840/kics.2025.50.8.1183)
Vol. 50, No. 8 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880