用执行结果筛选最佳SQL，小模型也能超大模型
Query and Conquer: Execution-Guided SQL Generation
- 生成多个SQL后，选执行结果最一致的
- 准确率超越o1、DeepSeek R1等大模型
- 推理成本降低30倍，适合工程落地
我们提出一种生成复杂输出的新方法，显著提升文本转SQL任务的准确性。该方法利用执行结果从多个候选SQL中选择语义最一致的版本，使小型、低成本模型在性能上超越计算量巨大的推理模型（如o1、o3-mini、DeepSeek R1），同时推理成本最高可降低30倍。该方法可无缝集成至现有模型，为实现顶尖水平的SQL生成提供了一条实用且可扩展的路径。
原文摘要 · Abstract (English)
We propose a novel approach for generating complex outputs that significantly improves accuracy in text-to-SQL tasks. Our method leverages execution results to select the most semantically consistent query from multiple candidates, enabling smaller, cost-effective models to surpass computationally intensive reasoning methods such as o1, o3-mini, and DeepSeek R1 while reducing inference cost by as much as 30 times. It integrates effortlessly with existing models, offering a practical and scalable pathway to state-of-the-art SQL generation.
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。