SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs

• URL: http://arxiv.org/abs/2505.13725v1
• Date: Mon, 19 May 2025 20:51:29 GMT
• Title: SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs
• Authors: Yu Guo, Dong Jin, Shenghao Ye, Shuangwu Chen, Jian Yang, Xiaobin Tan,
• Abstract summary: Large Language models (LLMs) have demonstrated significant potential in text-to- template reasoning tasks.<n>Yet a substantial performance gap persists between open-source models and their closed-source counterparts.<n>We introduce SQLForge, a novel approach for synthesizing reliable and diverse data.
• Score: 17.91039683592367
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language models (LLMs) have demonstrated significant potential in text-to-SQL reasoning tasks, yet a substantial performance gap persists between existing open-source models and their closed-source counterparts. In this paper, we introduce SQLForge, a novel approach for synthesizing reliable and diverse data to enhance text-to-SQL reasoning in LLMs. We improve data reliability through SQL syntax constraints and SQL-to-question reverse translation, ensuring data logic at both structural and semantic levels. We also propose an SQL template enrichment and iterative data domain exploration mechanism to boost data diversity. Building on the augmented data, we fine-tune a variety of open-source models with different architectures and parameter sizes, resulting in a family of models termed SQLForge-LM. SQLForge-LM achieves the state-of-the-art performance on the widely recognized Spider and BIRD benchmarks among the open-source models. Specifically, SQLForge-LM achieves EX accuracy of 85.7% on Spider Dev and 59.8% on BIRD Dev, significantly narrowing the performance gap with closed-source methods.

Related papers

• SLM-SQL: An Exploration of Small Language Models for Text-to-SQL [0.0]
  Small language models (SLMs) offer inherent advantages in inference speed and suitability for edge deployment.<n>We leverage recent advancements in post-training techniques to explore Textto- applications.<n> Experimental results validate the effectiveness and generalizability of our method.
  arXiv  Detail & Related papers  (2025-07-30T08:29:07Z)
• Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL [13.122218546167463]
  Large language models (LLMs) have significantly improved the performance of text-to- systems.<n>Many state-of-the-art (SOTA) approaches have overlooked the critical aspect of system robustness.
  arXiv  Detail & Related papers  (2024-12-17T04:22:22Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation [10.205010004198757]
  Text-to-generation enables non-experts to interact with databases via natural language.<n>Recent advances on large closed-source models like GPT-4 present challenges in accessibility, privacy, and latency.<n>We focus on developing small, efficient, and open-source text-to-generation models.
  arXiv  Detail & Related papers  (2024-10-16T18:03:24Z)
• Synthesizing Text-to-SQL Data from Weak and Strong LLMs [68.69270834311259]
  The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to- tasks. We introduce a synthetic data approach that combines data produced by larger, more powerful models with error information data generated by smaller, not well-aligned models.
  arXiv  Detail & Related papers  (2024-08-06T15:40:32Z)
• SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy [24.919119901664843]
  This paper introduces a robust system integrating open-source Large Language Models (LLMs) with a suite of tools to enhance query accuracy and usability. demonstrated by its leading performance on the Spider Leaderboard and deployment by Ant Group.
  arXiv  Detail & Related papers  (2024-07-19T06:01:57Z)
• RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL [48.516004807486745]
  Large language models (LLMs) with in-context learning have significantly improved the performance of text-to- task. We propose RB-, a novel retrieval-based framework for in-context prompt engineering. Experiment results demonstrate that our model achieves better performance than several competitive baselines on public datasets BIRD and Spider.
  arXiv  Detail & Related papers  (2024-07-11T08:19:58Z)
• SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data [54.69489315952524]
  "Prompt" is designed to improve the few-shot prompting capabilities of Text-to-LLMs. "Prompt" outperforms previous approaches for in-context learning with few labeled data by a large margin. We show that emphPrompt outperforms previous approaches for in-context learning with few labeled data by a large margin.
  arXiv  Detail & Related papers  (2023-11-06T05:24:06Z)
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [76.76046657162306]
  Large language models (LLMs) have emerged as a new paradigm for Text-to- task. Large language models (LLMs) have emerged as a new paradigm for Text-to- task.
  arXiv  Detail & Related papers  (2023-08-29T14:59:54Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.