mlsanityData to 7 Oct 2026

GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models

arXiv 2511.04710 ↗First posted 5 Nov 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL systems enable users to interact with structured databases using natural language, eliminating the need for specialized programming knowledge. In this work, we introduce GEMMA-SQL, a lightweight and efficient text-to-SQL model built upon the open-source Gemma 2B architecture. Unlike many large language models (LLMs), GEMMA-SQL is fine-tuned in a resource-efficient, iterative manner and can be deployed on low-cost hardware. Leveraging the SPIDER benchmark for training and evaluation, GEMMA-SQL combines multiple prompting strategies, including few-shot learning, to enhance SQL query generation accuracy. The instruction-tuned variant, GEMMA-SQL Instruct, achieves 66.8% Test-Suite accuracy and 63.3% Exact Set Match accuracy, outperforming several state-of-the-art baselines such as IRNet, RYANSQL, and CodeXDavinci. The proposed approach demonstrates that effective prompt design and targeted instruction tuning can significantly boost performance while maintaining high scalability and adaptability. These results position GEMMA-SQL as a practical, open-source alternative for robust and accessible text-to-SQL systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 73 references that are in the map. First posted on arXiv 5 Nov 2025.

Builds on

47 of 73 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  9. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  10. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  11. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  12. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
35 more
  1. 2023StarCoder: may the source be with you!cited by 790
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  3. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  4. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  5. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  6. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  7. 2021True Few-Shot Learning with Language Modelscited by 343
  8. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  9. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  10. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  11. 2016Language to Logical Form with Neural Attentioncited by 158
  12. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  13. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  14. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  15. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  16. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  17. 2023Retrieval meets Long Context Large Language Modelscited by 114
  18. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  19. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  20. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  21. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  22. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  23. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 50
  24. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  25. 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategiescited by 44
  26. 2023SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)cited by 42
  27. 2024MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLcited by 34
  28. 2013Lambda Dependency-Based Compositional Semanticscited by 26
  29. 2019Grammar-based Neural Text-to-SQL Generationcited by 23
  30. 2023SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Datacited by 16
  31. 2021mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformercited by 15
  32. 2024Structure Guided Large Language Model for SQL Generationcited by 9
  33. 2024Improving Self Consistency in LLMs through Probabilistic Tokenizationcited by 8
  34. 2024Context-Aware SQL Error Correction Using Few-Shot Learning -- A Novel Approach Based on NLQ, Error, and SQL Similaritycited by 2
  35. 2025End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generationcited by 2

Built on by

Not cited yet.