View in EDS HTML Full Text PDF Full Text

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

Saved in:
Bibliographic Details
Title: GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models.
Authors: Pandey, Hari Mohan1 (AUTHOR) hpandey@bournemouth.ac.uk, Gupta, Anshul2 (AUTHOR), Sarkar, Subham2 (AUTHOR), Tomer, Minakshi2 (AUTHOR), Johannes, Schneider3 (AUTHOR), Gong, Yan1 (AUTHOR)
Source: Applied Artificial Intelligence. Dec2025, Vol. 39 Issue 1, p1-38. 38p.
Subjects: Language models, SQL, Machine learning, Natural language processing, Open source software
Abstract: 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. [ABSTRACT FROM AUTHOR]
Copyright of Applied Artificial Intelligence is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 189934115
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Pandey%2C+Hari+Mohan%22">Pandey, Hari Mohan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hpandey@bournemouth.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Gupta%2C+Anshul%22">Gupta, Anshul</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sarkar%2C+Subham%22">Sarkar, Subham</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tomer%2C+Minakshi%22">Tomer, Minakshi</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Johannes%2C+Schneider%22">Johannes, Schneider</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gong%2C+Yan%22">Gong, Yan</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Applied+Artificial+Intelligence%22">Applied Artificial Intelligence</searchLink>. Dec2025, Vol. 39 Issue 1, p1-38. 38p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22SQL%22">SQL</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Open+source+software%22">Open source software</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Applied Artificial Intelligence is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=189934115
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/08839514.2025.2587371
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 38
        StartPage: 1
    Subjects:
      – SubjectFull: Language models
        Type: general
      – SubjectFull: SQL
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Open source software
        Type: general
    Titles:
      – TitleFull: GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Pandey, Hari Mohan
      – PersonEntity:
          Name:
            NameFull: Gupta, Anshul
      – PersonEntity:
          Name:
            NameFull: Sarkar, Subham
      – PersonEntity:
          Name:
            NameFull: Tomer, Minakshi
      – PersonEntity:
          Name:
            NameFull: Johannes, Schneider
      – PersonEntity:
          Name:
            NameFull: Gong, Yan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 08839514
          Numbering:
            – Type: volume
              Value: 39
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Applied Artificial Intelligence
              Type: main
ResultId 1