{"ID":2888707,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22478","arxiv_id":"2507.22478","title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","abstract":"Large language models (LLMs) have demonstrated strong performance in translating natural language questions into SQL queries (Text-to-SQL). In contrast, small language models (SLMs) ranging from 0.5B to 1.5B parameters currently underperform on Text-to-SQL tasks due to their limited logical reasoning capabilities. However, SLMs offer inherent advantages in inference speed and suitability for edge deployment. To explore their potential in Text-to-SQL applications, we leverage recent advancements in post-training techniques. Specifically, we used the open-source SynSQL-2.5M dataset to construct two derived datasets: SynSQL-Think-916K for SQL generation and SynSQL-Merge-Think-310K for SQL merge revision. We then applied supervised fine-tuning and reinforcement learning-based post-training to the SLM, followed by inference using a corrective self-consistency approach. Experimental results validate the effectiveness and generalizability of our method, SLM-SQL. On the BIRD development set, the five evaluated models achieved an average improvement of 31.4 points. Notably, the 0.5B model reached 56.87\\% execution accuracy (EX), while the 1.5B model achieved 67.08\\% EX. We will release our dataset, model, and code to github: https://github.com/CycloneBoy/slm_sql.","short_abstract":"Large language models (LLMs) have demonstrated strong performance in translating natural language questions into SQL queries (Text-to-SQL). In contrast, small language models (SLMs) ranging from 0.5B to 1.5B parameters currently underperform on Text-to-SQL tasks due to their limited logical reasoning capabilities. Howe...","url_abs":"https://arxiv.org/abs/2507.22478","url_pdf":"https://arxiv.org/pdf/2507.22478v1","authors":"[\"Lei Sheng\",\"Shuai-Shuai Xu\"]","published":"2025-07-30T08:29:07Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":611570,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888707,"paper_url":"https://arxiv.org/abs/2507.22478","paper_title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","repo_url":"https://github.com/CycloneBoy/slm_sql","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}