View in EDS HTML Full Text PDF Full Text

LLM-CR: LLM-enhanced course recommendation.

Saved in:
Bibliographic Details
Title: LLM-CR: LLM-enhanced course recommendation.
Authors: Jiang, Jianan1,2 (AUTHOR), Huang, Jiahui1,2 (AUTHOR) jiahuihuang@e.gzhu.edu.cn, Ren, Huali1,2 (AUTHOR), Long, Yucheng1,2 (AUTHOR) yuchenglong@e.gzhu.edu.cn, Sang, Haiwei3 (AUTHOR)
Source: International Journal of Educational Technology in Higher Education. 5/21/2026, Vol. 23 Issue 1, p1-28. 28p.
Subject Terms: *Prerequisites (Education), *Outcome-based education, *Online education, *Learning modules, Recommender systems, Knowledge representation (Information theory), Language models
Abstract: Recommender systems have become increasingly important in online learning platforms, where learners face a growing number of available courses and substantial variation in course quality and relevance. However, many existing course recommendation methods primarily rely on user–course interaction sequences and therefore often underutilize rich course semantic information, such as descriptions of learning objectives, covered concepts, and prerequisite-related content. This limitation is particularly problematic in educational settings, where learners' next-course choices are influenced not only by historical behavior but also by semantic relationships among courses. To address this issue, we propose LLM-CR, a recommendation framework that leverages large language models (LLMs) to enrich course representations with structured semantic information. Specifically, course metadata and textual descriptions are processed offline by an LLM to produce semantically informative course summaries, which are then encoded into dense representations and incorporated into the recommendation pipeline through a lightweight fusion module. In this way, LLM-CR augments conventional behavioral representations with course semantics related to topics, knowledge progression, and prerequisite-relevant information. The resulting model is evaluated in the standard next-course recommendation setting using ranking-based metrics. Experiments on six subject-specific subsets constructed from the XuetangX platform show that LLM-CR consistently improves recommendation performance over strong baseline methods, with especially notable gains on relatively sparse datasets. Additional analyses indicate that the proposed semantic augmentation introduces only modest extra complexity because the most expensive LLM processing is performed offline and reused across training and inference. These results suggest that incorporating LLM-derived semantic features is an effective and practical way to improve course recommendation quality. Highlights: We propose LLM-CR, a novel framework that synergistically combines LLM semanticunderstanding with sequential recommendation models for course recommendation. LLM-CR achieves significant performance improvements (up to 9.97\% on HR@5) withoutrequiring online LLM inference or architectural modifications to backbone models. Extensive experiments demonstrate LLM-CR's effectiveness across different backbones, withparticularly strong performance in sparse data and prerequisite-sensitive scenarios. LLM-CR provides a practical, plug-and-play solution that maintains computational efficiencywhile incorporating rich semantic knowledge. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Educational Technology in Higher Education is the property of Springer Nature 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: Education Research Complete
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: ehh
DbLabel: Education Research Complete
An: 193884578
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: LLM-CR: LLM-enhanced course recommendation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Jiang%2C+Jianan%22">Jiang, Jianan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Jiahui%22">Huang, Jiahui</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> jiahuihuang@e.gzhu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Ren%2C+Huali%22">Ren, Huali</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Long%2C+Yucheng%22">Long, Yucheng</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> yuchenglong@e.gzhu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Sang%2C+Haiwei%22">Sang, Haiwei</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Educational+Technology+in+Higher+Education%22">International Journal of Educational Technology in Higher Education</searchLink>. 5/21/2026, Vol. 23 Issue 1, p1-28. 28p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Prerequisites+%28Education%29%22">Prerequisites (Education)</searchLink><br />*<searchLink fieldCode="DE" term="%22Outcome-based+education%22">Outcome-based education</searchLink><br />*<searchLink fieldCode="DE" term="%22Online+education%22">Online education</searchLink><br />*<searchLink fieldCode="DE" term="%22Learning+modules%22">Learning modules</searchLink><br /><searchLink fieldCode="DE" term="%22Recommender+systems%22">Recommender systems</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+representation+%28Information+theory%29%22">Knowledge representation (Information theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Recommender systems have become increasingly important in online learning platforms, where learners face a growing number of available courses and substantial variation in course quality and relevance. However, many existing course recommendation methods primarily rely on user–course interaction sequences and therefore often underutilize rich course semantic information, such as descriptions of learning objectives, covered concepts, and prerequisite-related content. This limitation is particularly problematic in educational settings, where learners' next-course choices are influenced not only by historical behavior but also by semantic relationships among courses. To address this issue, we propose LLM-CR, a recommendation framework that leverages large language models (LLMs) to enrich course representations with structured semantic information. Specifically, course metadata and textual descriptions are processed offline by an LLM to produce semantically informative course summaries, which are then encoded into dense representations and incorporated into the recommendation pipeline through a lightweight fusion module. In this way, LLM-CR augments conventional behavioral representations with course semantics related to topics, knowledge progression, and prerequisite-relevant information. The resulting model is evaluated in the standard next-course recommendation setting using ranking-based metrics. Experiments on six subject-specific subsets constructed from the XuetangX platform show that LLM-CR consistently improves recommendation performance over strong baseline methods, with especially notable gains on relatively sparse datasets. Additional analyses indicate that the proposed semantic augmentation introduces only modest extra complexity because the most expensive LLM processing is performed offline and reused across training and inference. These results suggest that incorporating LLM-derived semantic features is an effective and practical way to improve course recommendation quality. Highlights: We propose LLM-CR, a novel framework that synergistically combines LLM semanticunderstanding with sequential recommendation models for course recommendation. LLM-CR achieves significant performance improvements (up to 9.97\% on HR@5) withoutrequiring online LLM inference or architectural modifications to backbone models. Extensive experiments demonstrate LLM-CR's effectiveness across different backbones, withparticularly strong performance in sparse data and prerequisite-sensitive scenarios. LLM-CR provides a practical, plug-and-play solution that maintains computational efficiencywhile incorporating rich semantic knowledge. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Educational Technology in Higher Education is the property of Springer Nature 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=ehh&AN=193884578
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1186/s41239-026-00590-0
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 1
    Subjects:
      – SubjectFull: Prerequisites (Education)
        Type: general
      – SubjectFull: Outcome-based education
        Type: general
      – SubjectFull: Online education
        Type: general
      – SubjectFull: Learning modules
        Type: general
      – SubjectFull: Recommender systems
        Type: general
      – SubjectFull: Knowledge representation (Information theory)
        Type: general
      – SubjectFull: Language models
        Type: general
    Titles:
      – TitleFull: LLM-CR: LLM-enhanced course recommendation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Jiang, Jianan
      – PersonEntity:
          Name:
            NameFull: Huang, Jiahui
      – PersonEntity:
          Name:
            NameFull: Ren, Huali
      – PersonEntity:
          Name:
            NameFull: Long, Yucheng
      – PersonEntity:
          Name:
            NameFull: Sang, Haiwei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 21
              M: 05
              Text: 5/21/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 23659440
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: International Journal of Educational Technology in Higher Education
              Type: main
ResultId 1