We propose a data-aware candidate selection method for NL2SQL translation based on separating instances and provenance. We implement this approach and evaluate it against three natural baselines on a subset of BIRD-DEV. Experiments show that our method significantly outperforms baselines when only two or three candidates are given and no consistency score is available. The code of our prototype can be found at https://github.com/staskikotx/SISelection

翻译：我们提出了一种基于分离实例和数据来源的数据感知候选选择方法，用于NL2SQL翻译。我们实现了该方法，并在BIRD-DEV子集上将其与三种自然基线进行了评估。实验表明，当仅给出两个或三个候选且无一致性分数可用时，我们的方法显著优于基线。我们原型的代码可在https://github.com/staskikotx/SISelection获取。