Publication Date

Spring 2026

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Engineering

Advisor

Bernardo Flores; Mahima Agumbe Suresh; Wencen Wu

Abstract

Current database interfaces limit users’ interaction to those with technical skills, creating timely roadblocks for non-technical professionals. Text-to-SQL aims to simplify database interactions by translating natural language questions into database queries, but long-standing challenges like question understanding, question-schema linking, and SQL generation have held the field back. In the AI era, foundational LLMs prove to be very capable of question understanding SQL, perform well in Schema Linking, Generation, and Evaluation tasks. However the cost to run these model is a hurdle for many organization with low funds and resources. Text-to-SQL solutions often operate across large enterprise size databases with, and Text-to-SQL solutions will often feed in all available tables creating an impact on the per-token cost, latency, and throughput of these systems. In this paper we propose several method to reduce the cost of Text-to-SQL solutions by using smaller language models and reduce the number of table schema processed. We evaluate each method on the BIRD dataset observing GPU resources it takes up by models, its per-token cost in cloud systems, and latency. In the end we suggest ways to make Text-to-SQL more accessible.

Download

Share

COinS