View in EDS

Exploring Shared Monitoring in Large Language Model (LLM)-Supported Online Collaborative Problem Solving for High-Cohesion and Low-Cohesion Groups

Saved in:
Bibliographic Details
Title: Exploring Shared Monitoring in Large Language Model (LLM)-Supported Online Collaborative Problem Solving for High-Cohesion and Low-Cohesion Groups
Language: English
Authors: Xiaoyun Liu (ORCID 0009-0003-9381-6534), Xu Du (ORCID 0000-0001-9069-6109), Jui-Long Hung, Hao Li (ORCID 0000-0001-5230-1348), Shuoqiu Yang (ORCID 0000-0002-3297-1026), Yiqian Xie (ORCID 0009-0008-9350-1168)
Source: Journal of Computer Assisted Learning. 2026 42(3).
Availability: Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
Peer Reviewed: Y
Page Count: 21
Publication Date: 2026
Document Type: Journal Articles
Reports - Research
Education Level: Higher Education
Postsecondary Education
Descriptors: Artificial Intelligence, Intervention, Technology Uses in Education, Cooperative Learning, Problem Solving, College Students, Group Unity, Foreign Countries, Scaffolding (Teaching Technique), Student Behavior
Geographic Terms: China
DOI: 10.1002/jcal.70249
ISSN: 0266-4909
1365-2729
Abstract: Background: Recent research increasingly highlights the central role of interventions in enhancing shared monitoring during collaborative problem-solving. However, traditional intervention approaches suffer from limitations in timeliness and adaptability. Large language model (LLM), equipped with deep semantic parsing and contextual perception, can dynamically detect latent challenges and provide targeted, timely, context-sensitive feedback. Objectives: This study examines how LLM-supported interventions affect group shared monitoring during dynamic CPS processes. Methods: This study designed a collaborative problem-solving platform integrated with LLM, and 28 students from a university in China participated in CPS activities. Chi-square tests, conditional random fields, linear mixed models and correlation analyses were adopted to examine the changes in both monitoring behaviour and equality of monitoring participation in high-cohesion (HCGs) and low-cohesion groups (LCGs) after LLM-supported group metacognitive scaffolding (LLM-GMS) intervention, as well as their effects on collaborative performance. Results and Conclusions: The results show that (1) LLM-GMS activated more socio-cognitive and behavioural monitoring in HCGs, whereas LCGs mainly exhibited heightened behavioural monitoring. (2) Descriptive analyses revealed divergent trends in monitoring participation equality across group types, with HCGs showing increased equality and LCGs exhibiting a decline. (3) In HCGs, socio-emotional monitoring was positively associated with collaborative performance, whereas participation equality and behavioural monitoring exhibited negative associations with collaborative performance. In contrast, among LCGs, behavioural monitoring was positively related to performance, whereas socio-cognitive monitoring was unexpectedly negatively associated with performance. Implications: These findings highlight that LLM-GMS can be a valuable tool for supporting collaborative learning, but its effectiveness depends on group characteristics and its implementation approach.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1506852
Database: ERIC
FullText Text:
  Availability: 0
Header DbId: eric
DbLabel: ERIC
An: EJ1506852
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Exploring Shared Monitoring in Large Language Model (LLM)-Supported Online Collaborative Problem Solving for High-Cohesion and Low-Cohesion Groups
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xiaoyun+Liu%22">Xiaoyun Liu</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0003-9381-6534">0009-0003-9381-6534</externalLink>)<br /><searchLink fieldCode="AR" term="%22Xu+Du%22">Xu Du</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-9069-6109">0000-0001-9069-6109</externalLink>)<br /><searchLink fieldCode="AR" term="%22Jui-Long+Hung%22">Jui-Long Hung</searchLink><br /><searchLink fieldCode="AR" term="%22Hao+Li%22">Hao Li</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-5230-1348">0000-0001-5230-1348</externalLink>)<br /><searchLink fieldCode="AR" term="%22Shuoqiu+Yang%22">Shuoqiu Yang</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0002-3297-1026">0000-0002-3297-1026</externalLink>)<br /><searchLink fieldCode="AR" term="%22Yiqian+Xie%22">Yiqian Xie</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0008-9350-1168">0009-0008-9350-1168</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Journal+of+Computer+Assisted+Learning%22"><i>Journal of Computer Assisted Learning</i></searchLink>. 2026 42(3).
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
– 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: Audience
  Label: Education Level
  Group: Audnce
  Data: <searchLink fieldCode="EL" term="%22Higher+Education%22">Higher Education</searchLink><br /><searchLink fieldCode="EL" term="%22Postsecondary+Education%22">Postsecondary Education</searchLink>
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Intervention%22">Intervention</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink><br /><searchLink fieldCode="DE" term="%22Cooperative+Learning%22">Cooperative Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+Solving%22">Problem Solving</searchLink><br /><searchLink fieldCode="DE" term="%22College+Students%22">College Students</searchLink><br /><searchLink fieldCode="DE" term="%22Group+Unity%22">Group Unity</searchLink><br /><searchLink fieldCode="DE" term="%22Foreign+Countries%22">Foreign Countries</searchLink><br /><searchLink fieldCode="DE" term="%22Scaffolding+%28Teaching+Technique%29%22">Scaffolding (Teaching Technique)</searchLink><br /><searchLink fieldCode="DE" term="%22Student+Behavior%22">Student Behavior</searchLink>
– Name: Subject
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22China%22">China</searchLink>
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1002/jcal.70249
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 0266-4909<br />1365-2729
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Recent research increasingly highlights the central role of interventions in enhancing shared monitoring during collaborative problem-solving. However, traditional intervention approaches suffer from limitations in timeliness and adaptability. Large language model (LLM), equipped with deep semantic parsing and contextual perception, can dynamically detect latent challenges and provide targeted, timely, context-sensitive feedback. Objectives: This study examines how LLM-supported interventions affect group shared monitoring during dynamic CPS processes. Methods: This study designed a collaborative problem-solving platform integrated with LLM, and 28 students from a university in China participated in CPS activities. Chi-square tests, conditional random fields, linear mixed models and correlation analyses were adopted to examine the changes in both monitoring behaviour and equality of monitoring participation in high-cohesion (HCGs) and low-cohesion groups (LCGs) after LLM-supported group metacognitive scaffolding (LLM-GMS) intervention, as well as their effects on collaborative performance. Results and Conclusions: The results show that (1) LLM-GMS activated more socio-cognitive and behavioural monitoring in HCGs, whereas LCGs mainly exhibited heightened behavioural monitoring. (2) Descriptive analyses revealed divergent trends in monitoring participation equality across group types, with HCGs showing increased equality and LCGs exhibiting a decline. (3) In HCGs, socio-emotional monitoring was positively associated with collaborative performance, whereas participation equality and behavioural monitoring exhibited negative associations with collaborative performance. In contrast, among LCGs, behavioural monitoring was positively related to performance, whereas socio-cognitive monitoring was unexpectedly negatively associated with performance. Implications: These findings highlight that LLM-GMS can be a valuable tool for supporting collaborative learning, but its effectiveness depends on group characteristics and its implementation 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: EJ1506852
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1506852
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/jcal.70249
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Intervention
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Cooperative Learning
        Type: general
      – SubjectFull: Problem Solving
        Type: general
      – SubjectFull: College Students
        Type: general
      – SubjectFull: Group Unity
        Type: general
      – SubjectFull: Foreign Countries
        Type: general
      – SubjectFull: Scaffolding (Teaching Technique)
        Type: general
      – SubjectFull: Student Behavior
        Type: general
      – SubjectFull: China
        Type: general
    Titles:
      – TitleFull: Exploring Shared Monitoring in Large Language Model (LLM)-Supported Online Collaborative Problem Solving for High-Cohesion and Low-Cohesion Groups
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xiaoyun Liu
      – PersonEntity:
          Name:
            NameFull: Xu Du
      – PersonEntity:
          Name:
            NameFull: Jui-Long Hung
      – PersonEntity:
          Name:
            NameFull: Hao Li
      – PersonEntity:
          Name:
            NameFull: Shuoqiu Yang
      – PersonEntity:
          Name:
            NameFull: Yiqian Xie
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 0266-4909
            – Type: issn-electronic
              Value: 1365-2729
          Numbering:
            – Type: volume
              Value: 42
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Journal of Computer Assisted Learning
              Type: main
ResultId 1