View in EDS PDF Full Text

Large Language Models for Educational Task Authoring: A Bebras Challenge Case Study

Saved in:
Bibliographic Details
Title: Large Language Models for Educational Task Authoring: A Bebras Challenge Case Study
Language: English
Authors: Leonard Busuttil (ORCID 0000-0003-3779-891X)
Source: Informatics in Education. 2026 25(1):37-57.
Availability: Vilnius University Institute of Mathematics and Informatics, Lithuanian Academy of Sciences. Akademjos str. 4, Vilnius LT 08663 Lithuania. Tel: +37-5-21-09300; Fax: +37-5-27-29209; e-mail: info@mii.vu.lt; Web site: https://infedu.vu.lt/journal/INFEDU
Peer Reviewed: Y
Page Count: 21
Publication Date: 2026
Document Type: Journal Articles
Reports - Research
Descriptors: Artificial Intelligence, Natural Language Processing, International Programs, Information Science, Computation, Thinking Skills, Computer Science, Educational Assessment, Test Content
ISSN: 1648-5831
2335-8971
Abstract: This study explores the application of large language models (LLMs) to create computational thinking tasks for the Bebras International Challenge through a single-case study approach. Using exemplar-based prompting with seven authentic Bebras tasks from the 2024 cycle as contextual input, a task was developed that was subsequently accepted for inclusion in the 2025 international Bebras challenge. Comparison with the exemplar tasks confirmed that the generated content drew from multiple sources rather than replicating any single task, combining grid-based constraint satisfaction, rule-based filtering, and logical deduction into a novel navigation puzzle with engaging narrative context. International expert reviewers evaluated the task using established Bebras quality criteria, confirming successful alignment with core pedagogical requirements including age-appropriateness, clarity, and cultural neutrality. However, two significant gaps emerged in the broader authoring workflow: accessibility compliance in the researcher-authored visual components and technical inaccuracies in the LLM-generated informatics framing. Following collaborative revision by international editors that addressed these concerns while preserving the LLM's creative contributions, the task achieved acceptance for international use. The findings reveal a collaborative pipeline comprising contextual preparation, LLM-guided generation, human technical implementation, expert community review, and collaborative revision. Results from this case suggest that LLMs can efficiently generate educationally sound creative foundations while requiring integrated human expertise to meet specialised standards and ensure inclusive design, with the task's acceptance providing encouraging evidence for the viability of this collaborative approach.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1506550
Database: ERIC
FullText Links:
  – Type: pdflink
    Url: https://content.ebscohost.com/cds/retrieve?content=AQICAHj0k_4E0hTGH8RJwT4gCJyBsGNe_WN95AvKlDbXJGqwxwGzB1YC2eRBLLWGLkQIBQCOAAAA4zCB4AYJKoZIhvcNAQcGoIHSMIHPAgEAMIHJBgkqhkiG9w0BBwEwHgYJYIZIAWUDBAEuMBEEDAot3mYqUyQ6S6cW_AIBEICBm3BiRw91GxC4ULN1cjVbRZVaX0Ga9ZiMQRlHEgZLfN7BhTdn-OTiQ4a1D7nRg71fSg8yrlHAn0W2-ZV3XWulUTdTVwRrNuc1Km7OCWotp-vAXaQCbeQc7zVS_lXWDaFn5lg5yq8R8WaO823R3MiN_h7QGM-X89bJly0kDDuT2YtpYEktKdsPqWqfJtGv9GDosJEY2kuj3D0WthVM
Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1506550
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: EJ1506550
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Large Language Models for Educational Task Authoring: A Bebras Challenge Case Study
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Leonard+Busuttil%22">Leonard Busuttil</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0003-3779-891X">0000-0003-3779-891X</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Informatics+in+Education%22"><i>Informatics in Education</i></searchLink>. 2026 25(1):37-57.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Vilnius University Institute of Mathematics and Informatics, Lithuanian Academy of Sciences. Akademjos str. 4, Vilnius LT 08663 Lithuania. Tel: +37-5-21-09300; Fax: +37-5-27-29209; e-mail: info@mii.vu.lt; Web site: https://infedu.vu.lt/journal/INFEDU
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 21
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2026
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– 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="%22International+Programs%22">International Programs</searchLink><br /><searchLink fieldCode="DE" term="%22Information+Science%22">Information Science</searchLink><br /><searchLink fieldCode="DE" term="%22Computation%22">Computation</searchLink><br /><searchLink fieldCode="DE" term="%22Thinking+Skills%22">Thinking Skills</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science%22">Computer Science</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+Assessment%22">Educational Assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Test+Content%22">Test Content</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 1648-5831<br />2335-8971
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study explores the application of large language models (LLMs) to create computational thinking tasks for the Bebras International Challenge through a single-case study approach. Using exemplar-based prompting with seven authentic Bebras tasks from the 2024 cycle as contextual input, a task was developed that was subsequently accepted for inclusion in the 2025 international Bebras challenge. Comparison with the exemplar tasks confirmed that the generated content drew from multiple sources rather than replicating any single task, combining grid-based constraint satisfaction, rule-based filtering, and logical deduction into a novel navigation puzzle with engaging narrative context. International expert reviewers evaluated the task using established Bebras quality criteria, confirming successful alignment with core pedagogical requirements including age-appropriateness, clarity, and cultural neutrality. However, two significant gaps emerged in the broader authoring workflow: accessibility compliance in the researcher-authored visual components and technical inaccuracies in the LLM-generated informatics framing. Following collaborative revision by international editors that addressed these concerns while preserving the LLM's creative contributions, the task achieved acceptance for international use. The findings reveal a collaborative pipeline comprising contextual preparation, LLM-guided generation, human technical implementation, expert community review, and collaborative revision. Results from this case suggest that LLMs can efficiently generate educationally sound creative foundations while requiring integrated human expertise to meet specialised standards and ensure inclusive design, with the task's acceptance providing encouraging evidence for the viability of this collaborative approach.
– 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: EJ1506550
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1506550
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
        StartPage: 37
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: International Programs
        Type: general
      – SubjectFull: Information Science
        Type: general
      – SubjectFull: Computation
        Type: general
      – SubjectFull: Thinking Skills
        Type: general
      – SubjectFull: Computer Science
        Type: general
      – SubjectFull: Educational Assessment
        Type: general
      – SubjectFull: Test Content
        Type: general
    Titles:
      – TitleFull: Large Language Models for Educational Task Authoring: A Bebras Challenge Case Study
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Leonard Busuttil
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 1648-5831
            – Type: issn-electronic
              Value: 2335-8971
          Numbering:
            – Type: volume
              Value: 25
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Informatics in Education
              Type: main
ResultId 1