View in EDS

Principled Transformers for Predictive Performance in Knowledge Tracing

Saved in:
Bibliographic Details
Title: Principled Transformers for Predictive Performance in Knowledge Tracing
Language: English
Authors: Kai Neubauer, Yannick Rudolph, Ulf Brefeld
Source: Journal of Educational Data Mining. 2026 18(1):89-112.
Availability: International Educational Data Mining. e-mail: jedm.editor@gmail.com; Web site: https://jedm.educationaldatamining.org/index.php/JEDM
Peer Reviewed: Y
Page Count: 24
Publication Date: 2026
Document Type: Journal Articles
Reports - Descriptive
Descriptors: Intelligent Tutoring Systems, Knowledge Level, Models, Prediction, Learning Processes, Best Practices, Benchmarking
ISSN: 2157-2100
Abstract: Knowledge tracing aims to model students' knowledge and abilities over time, which is crucial for intelligent tutoring systems. In this paper, we propose a straightforward model class, knowledge tracing set transformers" (KTSTs), specifically addressing predictive performance in "knowledge tracing tasks. KTSTs closely follow prominent transformer architectures and use an intuitive set-based representation for student interactions. We introduce "learnable ALiBi", which simplifies and improves upon a prevalent attention mechanism in knowledge tracing, and "MHSA aggregation", which readily allows incorporating an arbitrary number of additional, potentially more complex features per student interaction. We highlight and discuss flaws present in related approaches, which are overly complex and, in part, based on suboptimal design choices. We validate our design choices for KTSTs in experiments with real-world data and simulated learning sequences. Overall, we address "lessons learned" and propose a straightforward model that relies on best practices and establishes a new state-of-the-art on standardized benchmark datasets. Ultimately, KTSTs may serve as a simple but effective base model class for future research in knowledge tracing and intelligent tutoring systems.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1506613
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1506613
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: EJ1506613
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Principled Transformers for Predictive Performance in Knowledge Tracing
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kai+Neubauer%22">Kai Neubauer</searchLink><br /><searchLink fieldCode="AR" term="%22Yannick+Rudolph%22">Yannick Rudolph</searchLink><br /><searchLink fieldCode="AR" term="%22Ulf+Brefeld%22">Ulf Brefeld</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Journal+of+Educational+Data+Mining%22"><i>Journal of Educational Data Mining</i></searchLink>. 2026 18(1):89-112.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: International Educational Data Mining. e-mail: jedm.editor@gmail.com; Web site: https://jedm.educationaldatamining.org/index.php/JEDM
– 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: 2026
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Descriptive
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Intelligent+Tutoring+Systems%22">Intelligent Tutoring Systems</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+Level%22">Knowledge Level</searchLink><br /><searchLink fieldCode="DE" term="%22Models%22">Models</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction%22">Prediction</searchLink><br /><searchLink fieldCode="DE" term="%22Learning+Processes%22">Learning Processes</searchLink><br /><searchLink fieldCode="DE" term="%22Best+Practices%22">Best Practices</searchLink><br /><searchLink fieldCode="DE" term="%22Benchmarking%22">Benchmarking</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2157-2100
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Knowledge tracing aims to model students' knowledge and abilities over time, which is crucial for intelligent tutoring systems. In this paper, we propose a straightforward model class, knowledge tracing set transformers" (KTSTs), specifically addressing predictive performance in "knowledge tracing tasks. KTSTs closely follow prominent transformer architectures and use an intuitive set-based representation for student interactions. We introduce "learnable ALiBi", which simplifies and improves upon a prevalent attention mechanism in knowledge tracing, and "MHSA aggregation", which readily allows incorporating an arbitrary number of additional, potentially more complex features per student interaction. We highlight and discuss flaws present in related approaches, which are overly complex and, in part, based on suboptimal design choices. We validate our design choices for KTSTs in experiments with real-world data and simulated learning sequences. Overall, we address "lessons learned" and propose a straightforward model that relies on best practices and establishes a new state-of-the-art on standardized benchmark datasets. Ultimately, KTSTs may serve as a simple but effective base model class for future research in knowledge tracing and intelligent tutoring systems.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2026
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1506613
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1506613
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 89
    Subjects:
      – SubjectFull: Intelligent Tutoring Systems
        Type: general
      – SubjectFull: Knowledge Level
        Type: general
      – SubjectFull: Models
        Type: general
      – SubjectFull: Prediction
        Type: general
      – SubjectFull: Learning Processes
        Type: general
      – SubjectFull: Best Practices
        Type: general
      – SubjectFull: Benchmarking
        Type: general
    Titles:
      – TitleFull: Principled Transformers for Predictive Performance in Knowledge Tracing
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kai Neubauer
      – PersonEntity:
          Name:
            NameFull: Yannick Rudolph
      – PersonEntity:
          Name:
            NameFull: Ulf Brefeld
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 2157-2100
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Educational Data Mining
              Type: main
ResultId 1