mlsanityData to 14 Oct 2026

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

arXiv 2505.13725 ↗First posted 19 May 2025cs.CLcited by 11

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 16 of its 36 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

16 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL2 Oct

Other references · 15

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  5. 2024Qwen2 Technical Reportcited by 2,120
  6. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  7. 2023PaLM 2 Technical Reportcited by 1,162
  8. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  9. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 502
  10. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  11. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  12. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
3 more
  1. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
  2. 2024You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQLcited by 11
  3. 2024AnnotatedTables: A Large Tabular Dataset with Language Model Annotationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2026An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Datacited by 2
  2. 2026CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systemscited by 2
  3. 2026All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMscited by 2
  4. 2025SQL-Exchange: Transforming SQL Queries Across Domainscited by 1
  5. 2025Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translationcited by 1
  6. 2026Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learningcited by 1
  7. 2026RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learningcited by 0
  8. 2026SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesiscited by 0
  9. 2026Residual Skill Optimization for Text-to-SQL Ensemblescited by 0
  10. 2026Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQLcited by 0
  11. 2026FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
  2. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
  3. 2024Lucy: Think and Reason to Solve Text-to-SQL
  4. 2024Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models
  5. 2026SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation
  6. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
  7. 2025LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL
  8. 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL