{"ID":2857340,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09014","arxiv_id":"2510.09014","title":"LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction","abstract":"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, optimized with a hard-negative supervised contrastive objective to distinguish semantically similar but functionally irrelevant columns, and (ii) a SQL Generator fine-tuned in two stages-supervised fine-tuning followed by execution-guided reinforcement-enabling execution-guided self-correction without multi-candidate sampling, which is commonly required by prior LLM-based approaches. 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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.09014","url_pdf":"https://arxiv.org/pdf/2510.09014v2","authors":"[\"Shengmin Piao\",\"Jieun Lee\",\"Sanghyun Park\"]","published":"2025-10-10T05:27:47Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}