What type of study is this?

This is a Experimental Study study (also classified as: Quantitative Study).

October 22, 2025

Heuristic-Guided Text-to-SQL Translation with LLMs: Optimizing Natural Language Interfaces for Relational Databases

Key Points

Improved accuracy and execution efficiency were achieved using feedback loops in query optimization.
The integration of heuristic-based query rewriting has shown to enhance the interaction with relational databases.
Experimental validation used TPC-H and Mondial benchmarks, alongside a real-world database.
This approach highlights the significance of adaptive agents in natural language interfaces.

Abstract

Text-to-SQL mapping process plays a crucial role in enabling non-technical users to interact with relational databases using natural language. While Large Language Models (LLMs) have shown promising results in benchmark datasets, their performance in real-world settings often deteriorates. In this work, we propose a modular and adaptive agent that leverages the opensource LLM DeepSeek to perform translations with integrated feedback and query optimization. Our agent is prompt-engineered to refine query generation based on user or system-provided corrections. Using the TPC-H and Mondial benchmarks, as well as a real-world database, we demonstrate improved accuracy and execution efficiency, highlighting the impact of feedback loops and heuristic-based query rewriting.

KI fragen

Bookmark