Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text

TL;DR

This paper introduces a new benchmark dataset and a graph-aware in-context learning approach for translating SQL queries into natural language, improving explanation quality and dataset robustness for security and educational applications.

Contribution

It repurposes Text2SQL datasets for SQL2Text, employing an iterative GPT-4o-based prompt and graph-aware sample selection to enhance few-shot learning performance.

Findings

Graph-aware sample selection improves BLEU scores by up to 39%.

Using SQL's inherent graph properties outperforms random sampling.

The approach is effective with smaller, efficient LLMs.

Abstract

Large Language Models (LLMs) have demonstrated remarkable performance in various NLP tasks, including semantic parsing, which translates natural language into formal code representations. However, the reverse process, translating code into natural language, termed semantic captioning, has received less attention. This task is becoming increasingly important as LLMs are integrated into platforms for code generation, security analysis, and educational purposes. In this paper, we focus on the captioning of SQL query (SQL2Text) to address the critical need for understanding and explaining SQL queries in an era where LLM-generated code poses potential security risks. We repurpose Text2SQL datasets for SQL2Text by introducing an iterative ICL prompt using GPT-4o to generate multiple additional utterances, which enhances the robustness of the datasets for the reverse task. We conduct our experiments using in-context learning (ICL) based on different sample selection methods, emphasizing smaller, more computationally efficient LLMs. Our findings demonstrate that leveraging the inherent graph properties of SQL for ICL sample selection significantly outperforms random selection by up to 39% on BLEU score and provides better results than alternative methods. Dataset and codes are published: https://github.com/aliwister/ast-icl.