开源小模型+自修正机制，让非专业人士也能准确将自然语言转为SQL。
DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQL
- 用2万+样本微调小模型，提升自然语言转SQL的效率。
- 在Spider数据集上达到87.2%准确率，代码正确性显著提升。
- 适合数据查询新手和需规避闭源模型风险的团队使用。
为解决将自然语言查询转换为SQL命令的关键问题，我们提出一套轻量级微调模型与自修正机制，旨在降低非专家用户的数据访问与分析门槛，并缓解闭源大模型带来的风险。具体而言，我们构建了包含超过2万条样本的Text-to-SQL数据集及偏好数据集，以提升该领域生成效率。为进一步保障生成代码的有效性，系统集成了一个代码校正模块。我们的DataGpt-sql系统在Spider-dev上取得了87.2%的准确率，充分验证了该方案在文本转SQL任务中的有效性。代码、数据与模型均已开源，详见 https://github.com/CainiaoTechAi/datagpt-sql-7b。
原文摘要 · Abstract (English)
In addressing the pivotal role of translating natural language queries into SQL commands, we propose a suite of compact, fine-tuned models and self-refine mechanisms to democratize data access and analysis for non-expert users, mitigating risks associated with closed-source Large Language Models. Specifically, we constructed a dataset of over 20K sample for Text-to-SQL as well as the preference dateset, to improve the efficiency in the domain of SQL generation. To further ensure code validity, a code corrector was integrated into the model. Our system, DataGpt-sql, achieved 87.2\% accuracy on the spider-dev, respectively, showcasing the effectiveness of our solution in text-to-SQL conversion tasks. Our code, data, and models are available at \url{https://github.com/CainiaoTechAi/datagpt-sql-7b}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。