@inproceedings{piao-etal-2026-lite,
    title = "{L}it{E}-{SQL}: A Lightweight and Efficient Text-to-{SQL} Framework with Vector-based Schema Linking and Execution-Guided Self-Correction",
    author = "Piao, Shengmin  and
      Lee, Jieun  and
      Park, Sanghyun",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.186/",
    pages = "3593--3608",
    ISBN = "979-8-89176-386-9",
    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 raises 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 2{\texttimes} to 30{\texttimes} 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."
}