View in EDS

Math-LLMs: AI Cyberinfrastructure with Pre-Trained Transformers for Math Education

Saved in:
Bibliographic Details
Title: Math-LLMs: AI Cyberinfrastructure with Pre-Trained Transformers for Math Education
Language: English
Authors: Fan Zhang, Chenglu Li, Owen Henkel, Wanli Xing (ORCID 0000-0002-1446-889X), Sami Baral, Neil Heffernan, Hai Li
Source: International Journal of Artificial Intelligence in Education. 2025 35(2):509-532.
Availability: Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/
Peer Reviewed: Y
Page Count: 24
Publication Date: 2025
Document Type: Journal Articles
Reports - Research
Education Level: Elementary Secondary Education
Descriptors: Artificial Intelligence, Natural Language Processing, Mathematics Education, Elementary Secondary Education, Computer Uses in Education
DOI: 10.1007/s40593-024-00416-y
ISSN: 1560-4292
1560-4306
Abstract: In recent years, the pre-training of Large Language Models (LLMs) in the educational domain has garnered significant attention. However, a discernible gap exists in the application of these models to mathematics education. This study aims to bridge this gap by pre-training LLMs on authentic K-12 mathematical dialogue datasets. Our research is structured around three primary research questions (RQs) that investigate the impact of fine-tuning data size and pre-training in downstream Natural Language Processing (NLP) tasks, and the efficacy of LLMs in text generation tasks within the mathematical context. Our findings indicate that data size plays a pivotal role in the performance of LLMs in downstream NLP tasks, with larger datasets yielding more consistent and improved results. Furthermore, pre-trained models consistently outperformed their non-pre-trained counterparts, emphasizing the importance of leveraging prior knowledge in LLMs. In the realm of text generation, we found that our model can not only enhance mathematical understanding and performance on downstream math tasks but also generate more engaging and human-like language.
Abstractor: As Provided
Entry Date: 2025
Accession Number: EJ1488404
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: EJ1488404
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Math-LLMs: AI Cyberinfrastructure with Pre-Trained Transformers for Math Education
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Fan+Zhang%22">Fan Zhang</searchLink><br /><searchLink fieldCode="AR" term="%22Chenglu+Li%22">Chenglu Li</searchLink><br /><searchLink fieldCode="AR" term="%22Owen+Henkel%22">Owen Henkel</searchLink><br /><searchLink fieldCode="AR" term="%22Wanli+Xing%22">Wanli Xing</searchLink> (ORCID <externalLink term="http://orcid.org/0000-0002-1446-889X">0000-0002-1446-889X</externalLink>)<br /><searchLink fieldCode="AR" term="%22Sami+Baral%22">Sami Baral</searchLink><br /><searchLink fieldCode="AR" term="%22Neil+Heffernan%22">Neil Heffernan</searchLink><br /><searchLink fieldCode="AR" term="%22Hai+Li%22">Hai Li</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22International+Journal+of+Artificial+Intelligence+in+Education%22"><i>International Journal of Artificial Intelligence in Education</i></searchLink>. 2025 35(2):509-532.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 24
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2025
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Audience
  Label: Education Level
  Group: Audnce
  Data: <searchLink fieldCode="EL" term="%22Elementary+Secondary+Education%22">Elementary Secondary Education</searchLink>
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+Language+Processing%22">Natural Language Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematics+Education%22">Mathematics Education</searchLink><br /><searchLink fieldCode="DE" term="%22Elementary+Secondary+Education%22">Elementary Secondary Education</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Uses+in+Education%22">Computer Uses in Education</searchLink>
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1007/s40593-024-00416-y
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 1560-4292<br />1560-4306
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In recent years, the pre-training of Large Language Models (LLMs) in the educational domain has garnered significant attention. However, a discernible gap exists in the application of these models to mathematics education. This study aims to bridge this gap by pre-training LLMs on authentic K-12 mathematical dialogue datasets. Our research is structured around three primary research questions (RQs) that investigate the impact of fine-tuning data size and pre-training in downstream Natural Language Processing (NLP) tasks, and the efficacy of LLMs in text generation tasks within the mathematical context. Our findings indicate that data size plays a pivotal role in the performance of LLMs in downstream NLP tasks, with larger datasets yielding more consistent and improved results. Furthermore, pre-trained models consistently outperformed their non-pre-trained counterparts, emphasizing the importance of leveraging prior knowledge in LLMs. In the realm of text generation, we found that our model can not only enhance mathematical understanding and performance on downstream math tasks but also generate more engaging and human-like language.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2025
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1488404
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1488404
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s40593-024-00416-y
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 509
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Mathematics Education
        Type: general
      – SubjectFull: Elementary Secondary Education
        Type: general
      – SubjectFull: Computer Uses in Education
        Type: general
    Titles:
      – TitleFull: Math-LLMs: AI Cyberinfrastructure with Pre-Trained Transformers for Math Education
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Fan Zhang
      – PersonEntity:
          Name:
            NameFull: Chenglu Li
      – PersonEntity:
          Name:
            NameFull: Owen Henkel
      – PersonEntity:
          Name:
            NameFull: Wanli Xing
      – PersonEntity:
          Name:
            NameFull: Sami Baral
      – PersonEntity:
          Name:
            NameFull: Neil Heffernan
      – PersonEntity:
          Name:
            NameFull: Hai Li
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 1560-4292
            – Type: issn-electronic
              Value: 1560-4306
          Numbering:
            – Type: volume
              Value: 35
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: International Journal of Artificial Intelligence in Education
              Type: main
ResultId 1