Currently, the in-context learning method based on large language models (LLMs) has become the mainstream of text-to-SQL research. Previous works have discussed how to select demonstrations related to the user question from a human-labeled demonstration pool. However, human labeling suffers from the limitations of insufficient diversity and high labeling overhead. Therefore, in this paper, we discuss how to measure and improve the diversity of the demonstrations for text-to-SQL. We present a metric to measure the diversity of the demonstrations and analyze the insufficient of the existing labeled data by experiments. Based on the above discovery, we propose fusing iteratively for demonstrations (Fused) to build a high-diversity demonstration pool through human-free multiple-iteration synthesis, improving diversity and lowering label cost. Our method achieves an average improvement of 3.2% and 5.0% with and without human labeling on several mainstream datasets, which proves the effectiveness of Fused.

翻译：当前，基于大语言模型（LLM）的上下文学习方法已成为文本到SQL研究的主流。先前的研究探讨了如何从人工标注的演示池中筛选与用户问题相关的演示示例。然而，人工标注存在多样性不足和标注成本高昂的局限性。因此，本文探讨如何量化和提升文本到SQL任务中演示示例的多样性。我们提出了一种衡量演示多样性的指标，并通过实验分析了现有标注数据在多样性方面的不足。基于上述发现，我们提出迭代融合演示方法（Fused），通过无需人工参与的多轮迭代合成构建高多样性演示池，从而提升多样性并降低标注成本。在多个主流数据集上，我们的方法在有人工标注和无人工标注的情况下分别实现了平均3.2%和5.0%的性能提升，验证了Fused方法的有效性。