CLMay 13, 2024

MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation

arXiv:2405.07467v1126 citationsh-index: 4COLING
Originality Highly original
AI Analysis

This work addresses the challenge of generating accurate SQL queries from natural language for complex schemas, which is crucial for database users and developers, representing a strong specific gain rather than a foundational advancement.

The paper tackled the problem of improving text-to-SQL generation for complex databases by addressing sensitivity to prompts, resulting in execution accuracies of 65.5% on BIRD and 89.6% on Spider benchmarks, significantly outperforming previous in-context learning methods.

Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of human experts on benchmarks that include complex schemas and queries, such as BIRD. This study considers the sensitivity of LLMs to the prompts and introduces a novel approach that leverages multiple prompts to explore a broader search space for possible answers and effectively aggregate them. Specifically, we robustly refine the database schema through schema linking using multiple prompts. Thereafter, we generate various candidate SQL queries based on the refined schema and diverse prompts. Finally, the candidate queries are filtered based on their confidence scores, and the optimal query is obtained through a multiple-choice selection that is presented to the LLM. When evaluated on the BIRD and Spider benchmarks, the proposed method achieved execution accuracies of 65.5\% and 89.6\%, respectively, significantly outperforming previous ICL-based methods. Moreover, we established a new SOTA performance on the BIRD in terms of both the accuracy and efficiency of the generated queries.

Foundations

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

Your Notes