View in EDS

Prompt Engineering as Cognitive Scaffolding for Ethical and Explanatory Quality in AI-Mediated Financial Learning

Saved in:
Bibliographic Details
Title: Prompt Engineering as Cognitive Scaffolding for Ethical and Explanatory Quality in AI-Mediated Financial Learning
Language: English
Authors: Kehinde Aruleba, Ebenezer Esenogho, Cameron Modisane
Source: Discover Education. 2026 5.
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: 17
Publication Date: 2026
Document Type: Journal Articles
Reports - Research
Descriptors: Prompting, Engineering, Cognitive Processes, Scaffolding (Teaching Technique), Ethics, Educational Quality, Artificial Intelligence, Technology Uses in Education, Financial Education, Natural Language Processing, Scores
DOI: 10.1007/s44217-026-01134-4
ISSN: 2731-5525
Abstract: Background: Large language models (LLMs) are increasingly used in personal finance education, yet the role of instructional prompt design in shaping explanatory quality and ethical responsiveness remains underexplored. This matters because trustworthy financial guidance and instruction depend on clarity, accuracy, and appropriately cautionary framing. Method: We conducted a Design-Based Research (DBR) Phase 1 artefact-validation study using content analysis of 120 GPT-4-turbo (May 2025) generations. Ninety diagnostic prompts varied linguistic framing, cognitive level, and ethical intent; thirty Phase 1b prompts instantiated a derived taxonomy. Two expert reviewers scored outputs (0-3) for financial accuracy, conceptual clarity, and ethical tone (inter-rater reliability: κ = 0.82 ). Results: Prompt form was a pedagogical determinant of content quality. Procedural prompts outperformed interrogatives on clarity (U = 418, p < 0.001, r = 0.42) and accuracy (U = 457, p < 0.01, r = 0.31). Ethical anchoring raised ethical tone (median 2.78 vs. 2.31; Cliff's δ = 0.46, p < 0.001) with a modest accuracy trade-off (δ = -0.18, p = 0.04). Taxonomy-guided prompting increased medians for clarity (+0.46 to 2.92), accuracy (+0.41 to 2.81) and ethical tone (+0.37 to 2.71), and reduced low-quality outliers from 18% to 4% (x² = 7.91, p = 0.005), evidencing higher instructional reliability at the content level. Conclusion: The prompt taxonomy, validated here at the content level, operationalises three design principles -- Guided Explanation, Contextualised Inquiry, and Comparative Reasoning. These links prompt forms to instructional functions via structural scaffolding and situated relevance. Treating prompt engineering as instructional design can systematically improve AI-mediated educational content in high-stakes finance. DBR Phase 2 will test impacts on learner outcomes (decision quality, self-regulation, calibrated trust) and robustness across models and retrieval-augmented settings.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1508599
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: EJ1508599
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Prompt Engineering as Cognitive Scaffolding for Ethical and Explanatory Quality in AI-Mediated Financial Learning
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kehinde+Aruleba%22&quot;&gt;Kehinde Aruleba&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Ebenezer+Esenogho%22&quot;&gt;Ebenezer Esenogho&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Cameron+Modisane%22&quot;&gt;Cameron Modisane&lt;/searchLink&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;SO&quot; term=&quot;%22Discover+Education%22&quot;&gt;&lt;i&gt;Discover Education&lt;/i&gt;&lt;/searchLink&gt;. 2026 5.
– 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: 17
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2026
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles&lt;br /&gt;Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Prompting%22&quot;&gt;Prompting&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Engineering%22&quot;&gt;Engineering&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Cognitive+Processes%22&quot;&gt;Cognitive Processes&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Scaffolding+%28Teaching+Technique%29%22&quot;&gt;Scaffolding (Teaching Technique)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Ethics%22&quot;&gt;Ethics&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Educational+Quality%22&quot;&gt;Educational Quality&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Artificial+Intelligence%22&quot;&gt;Artificial Intelligence&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Technology+Uses+in+Education%22&quot;&gt;Technology Uses in Education&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Financial+Education%22&quot;&gt;Financial Education&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Natural+Language+Processing%22&quot;&gt;Natural Language Processing&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Scores%22&quot;&gt;Scores&lt;/searchLink&gt;
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1007/s44217-026-01134-4
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2731-5525
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Large language models (LLMs) are increasingly used in personal finance education, yet the role of instructional prompt design in shaping explanatory quality and ethical responsiveness remains underexplored. This matters because trustworthy financial guidance and instruction depend on clarity, accuracy, and appropriately cautionary framing. Method: We conducted a Design-Based Research (DBR) Phase 1 artefact-validation study using content analysis of 120 GPT-4-turbo (May 2025) generations. Ninety diagnostic prompts varied linguistic framing, cognitive level, and ethical intent; thirty Phase 1b prompts instantiated a derived taxonomy. Two expert reviewers scored outputs (0-3) for financial accuracy, conceptual clarity, and ethical tone (inter-rater reliability: κ = 0.82 ). Results: Prompt form was a pedagogical determinant of content quality. Procedural prompts outperformed interrogatives on clarity (U = 418, p &lt; 0.001, r = 0.42) and accuracy (U = 457, p &lt; 0.01, r = 0.31). Ethical anchoring raised ethical tone (median 2.78 vs. 2.31; Cliff&#39;s δ = 0.46, p &lt; 0.001) with a modest accuracy trade-off (δ = -0.18, p = 0.04). Taxonomy-guided prompting increased medians for clarity (+0.46 to 2.92), accuracy (+0.41 to 2.81) and ethical tone (+0.37 to 2.71), and reduced low-quality outliers from 18% to 4% (x&#178; = 7.91, p = 0.005), evidencing higher instructional reliability at the content level. Conclusion: The prompt taxonomy, validated here at the content level, operationalises three design principles -- Guided Explanation, Contextualised Inquiry, and Comparative Reasoning. These links prompt forms to instructional functions via structural scaffolding and situated relevance. Treating prompt engineering as instructional design can systematically improve AI-mediated educational content in high-stakes finance. DBR Phase 2 will test impacts on learner outcomes (decision quality, self-regulation, calibrated trust) and robustness across models and retrieval-augmented settings.
– 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: EJ1508599
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1508599
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s44217-026-01134-4
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
    Subjects:
      – SubjectFull: Prompting
        Type: general
      – SubjectFull: Engineering
        Type: general
      – SubjectFull: Cognitive Processes
        Type: general
      – SubjectFull: Scaffolding (Teaching Technique)
        Type: general
      – SubjectFull: Ethics
        Type: general
      – SubjectFull: Educational Quality
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Financial Education
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Scores
        Type: general
    Titles:
      – TitleFull: Prompt Engineering as Cognitive Scaffolding for Ethical and Explanatory Quality in AI-Mediated Financial Learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kehinde Aruleba
      – PersonEntity:
          Name:
            NameFull: Ebenezer Esenogho
      – PersonEntity:
          Name:
            NameFull: Cameron Modisane
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 2731-5525
          Numbering:
            – Type: volume
              Value: 5
          Titles:
            – TitleFull: Discover Education
              Type: main
ResultId 1