SQL-to-Text Generation with Weighted-AST Few-Shot Prompting

TL;DR

This paper introduces Weighted-AST retrieval with prompting, a novel method that improves SQL-to-text generation by integrating structural query representations and LLM prompting, leading to more accurate and faithful natural language descriptions of SQL queries.

Contribution

The work proposes a structure-aware prompting technique using Weighted-AST retrieval to enhance the semantic fidelity of SQL-to-text generation with large language models.

Findings

Outperforms baselines by up to +17.24% in execution accuracy

Achieves higher exact match and semantic fidelity in human evaluations

Maintains competitive runtime performance

Abstract

SQL-to-Text generation aims at translating structured SQL queries into natural language descriptions, thereby facilitating comprehension of complex database operations for non-technical users. Although large language models (LLMs) have recently demonstrated promising results, current methods often fail to maintain the exact semantics of SQL queries, particularly when there are multiple possible correct phrasings. To address this problem, our work proposes Weighted-AST retrieval with prompting, an architecture that integrates structural query representations and LLM prompting. This method retrieves semantically relevant examples as few-shot prompts using a similarity metric based on an Abstract Syntax Tree (AST) with learned feature weights. Our structure-aware prompting technique ensures that generated descriptions are both fluent and faithful to the original query logic. Numerous experiments on three benchmark datasets - Spider, SParC, and CoSQL show that our method outperforms the current baselines by up to +17.24% in execution Accuracy (EX), performs superior in Exact Match (EM) and provides more consistent semantic fidelity when evaluated by humans, all while preserving competitive runtime performance. These results demonstrate that Weighted-AST prompting is a scalable and effective method for deriving natural language explanations from structured database queries.