DBAICLLGDec 4, 2023

Fine-Tuning Language Models for Context-Specific SQL Query Generation

arXiv:2312.02251v18 citationsh-index: 2Has Code
Originality Incremental advance
AI Analysis

This work addresses making relational databases more accessible to non-specialists through natural language interfaces, but it is incremental as it applies existing fine-tuning methods to a specific domain.

The paper tackled the problem of generating SQL queries from natural language in the retail domain by fine-tuning open-source LLMs on synthetic datasets, resulting in Code-Llama achieving accuracy rates of 81.58% for Snowflake SQL and 82.66% for GoogleSQL, outperforming GPT-4 in zero-shot settings.

The ability to generate SQL queries from natural language has significant implications for making data accessible to non-specialists. This paper presents a novel approach to fine-tuning open-source large language models (LLMs) for the task of transforming natural language into SQL queries within the retail domain. We introduce models specialized in generating SQL queries, trained on synthetic datasets tailored to the Snowflake SQL and GoogleSQL dialects. Our methodology involves generating a context-specific dataset using GPT-4, then fine-tuning three open-source LLMs(Starcoder Plus, Code-Llama, and Mistral) employing the LoRa technique to optimize for resource constraints. The fine-tuned models demonstrate superior performance in zero-shot settings compared to the baseline GPT-4, with Code-Llama achieving the highest accuracy rates, at 81.58% for Snowflake SQL and 82.66% for GoogleSQL. These results underscore the effectiveness of fine-tuning LLMs on domain-specific tasks and suggest a promising direction for enhancing the accessibility of relational databases through natural language interfaces.

Foundations

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

Your Notes