LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction
It provides a practical solution for privacy-sensitive and resource-constrained settings by enabling efficient database interaction for non-experts, though it is incremental as it builds on existing lightweight model approaches.
The paper tackled the Text-to-SQL task by introducing LitE-SQL, a lightweight framework that uses vector-based schema linking and execution-guided self-correction, achieving 72.10% execution accuracy on BIRD and 88.45% on Spider 1.0 with 2x to 30x fewer parameters than LLM-based methods.
The Text-to-SQL task translates natural language questions into SQL queries, enabling intuitive database interaction for non-experts. While recent methods leveraging Large Language Models (LLMs) achieve strong performance, their reliance on proprietary models raise concerns about deployment feasibility and data privacy. In this work, we introduce LitE-SQL, a Lightweight and Efficient framework with two components: (i) a Schema Retriever that performs efficient schema linking using a vector database of pre-computed schema embeddings, and (ii) a SQL Generator fine-tuned in two stages-supervised fine-tuning followed by execution-guided reinforcement-enabling self-correction without costly multi-candidate generation. On BIRD, LitE-SQL achieves 72.10% execution accuracy, and on Spider 1.0 it reaches 88.45%, demonstrating comparable or superior performance to LLM-based methods despite using 2x to 30x fewer parameters. Our findings demonstrate that high-quality Text-to-SQL generation is feasible with lightweight models, offering a practical solution for privacy-sensitive and resource-constrained settings.