Master Thesis Online
How do Large Language Model architecture choices affect text-to-SQL performance and efficiency ?
Romoli, Raphaël 
Promotor(s) :
Louppe, Gilles
Date of defense : 30-Jun-2025/1-Jul-2025 • Permalink : http://hdl.handle.net/2268.2/23189
Details
| Title : | How do Large Language Model architecture choices affect text-to-SQL performance and efficiency ? |
| Author : | Romoli, Raphaël
|
| Date of defense : | 30-Jun-2025/1-Jul-2025 |
| Advisor(s) : | Louppe, Gilles
|
| Committee's member(s) : | Remondini, Leonardo
Huynh-Thu, Vân Anh
Debruyne, Christophe
|
| Language : | English |
| Discipline(s) : | Engineering, computing & technology > Civil engineering |
| Institution(s) : | Université de Liège, Liège, Belgique |
| Degree: | Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems" |
| Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[en] This reseach respond to the question: How do single-agent and multi-agent LLM architectures, varying in context delivery methods (static vs. dynamic schema injection), model selection (GPT-3.5 vs. GPT-4o), and schema retrieval impact accuracy, cost efficiency, and scalability for complex text-to-SQL generation?
File(s)
Document(s)
Resume_raphael_romoli.pdf
Description: Resumé 1 page
Size: 148.2 kB
Format: Adobe PDF
Cite this master thesis
All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.
