CLMay 23, 2023

Exploring Chain-of-Thought Style Prompting for Text-to-SQL

arXiv:2305.14215v2115 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of text-to-SQL parsing for database query generation, showing incremental improvements over existing prompting techniques.

The paper tackles the problem of improving text-to-SQL parsing with large language models by enhancing their multi-step reasoning ability through chain-of-thought style prompting, resulting in absolute gains of 5.2 and 6.5 points on benchmark datasets compared to standard methods.

In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. However, its performance on text-to-SQL parsing still has much room for improvement. In this paper, we hypothesize that a crucial aspect of LLMs to improve for text-to-SQL parsing is their multi-step reasoning ability. Thus, we systematically study how to enhance LLMs' reasoning ability through chain of thought (CoT) style prompting, including the original chain-of-thought prompting (Wei et al., 2022b) and least-to-most prompting (Zhou et al., 2023). Our experiments demonstrate that iterative prompting as in Zhou et al. (2023) may be unnecessary for text-to-SQL parsing, and using detailed reasoning steps tends to have more error propagation issues. Based on these findings, we propose a new CoT-style prompting method for text-to-SQL parsing. It brings 5.2 and 6.5 point absolute gains on the Spider development set and the Spider Realistic set, respectively, compared to the standard prompting method without reasoning steps; 2.4 and 1.5 point absolute gains, compared to the least-to-most prompting method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes