Academic Journal
View in EDS

LLMs in Problem-Based Learning: The Grounding Issue.

Bibliographic Details
Title: LLMs in Problem-Based Learning: The Grounding Issue.
Authors: Sariyar M; Bern University of Applied Sciences, IODA Institute, Bern, Switzerland.
Source: Studies in health technology and informatics [Stud Health Technol Inform] 2026 Jun 29; Vol. 338, pp. 698-702.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9214582 Publication Model: Print Cited Medium: Internet ISSN: 1879-8365 (Electronic) Linking ISSN: 09269630 NLM ISO Abbreviation: Stud Health Technol Inform Subsets: MEDLINE
Imprint Name(s): Original Publication: Amsterdam ; Washington, DC : IOS Press, 1991-
MeSH Terms: Problem-Based Learning*/methods , Education, Medical*/methods , Kidney Neoplasms*/diagnosis , Large Language Models*, Humans ; Generative Artificial Intelligence
Abstract: Large language models (LLMs) are increasingly used in medical education, including in problem-based learning (PBL). Their ability to summarize cases, generate differential diagnoses, and structure discussion raises the question of whether they might eventually replace PBL rather than merely support it. This paper offers a conceptual analysis of that question, using a renal-tumor PBL case derived from recent ChatGPT-assisted teaching research as an illustrative use case. It distinguishes among semantic support, representational uncertainty, and situated uncertainty. LLMs can contribute substantially at the first two levels: they can reformulate cases, identify missing information, keep multiple diagnostic possibilities in play, and suggest coherent next steps. What they do not reproduce is the situated uncertainty through which PBL forms judgment in interaction with peers and tutors. More tools, retrieval, modalities, or sensor input may enrich representation, but they do not by themselves close this gap. The paper therefore argues that LLMs can augment PBL in important ways but do not replace its role in the formation of clinical judgment.
Contributed Indexing: Keywords: grounding; large language models; medical education; problem-based learning
Entry Date(s): Date Created: 20260703 Date Completed: 20260703 Latest Revision: 20260703
Update Code: 20260703
DOI: 10.3233/SHTI260935
PMID: 42394097
Database: MEDLINE
FullText Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 42394097
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: LLMs in Problem-Based Learning: The Grounding Issue.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Sariyar+M%22">Sariyar M</searchLink>; Bern University of Applied Sciences, IODA Institute, Bern, Switzerland.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%229214582%22">Studies in health technology and informatics</searchLink> [Stud Health Technol Inform] 2026 Jun 29; Vol. 338, pp. 698-702.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22IOS+Press%22">IOS Press </searchLink><i>Country of Publication: </i>Netherlands <i>NLM ID: </i>9214582 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1879-8365 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2209269630%22">09269630 </searchLink><i>NLM ISO Abbreviation: </i>Stud Health Technol Inform <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: Amsterdam ; Washington, DC : IOS Press, 1991-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Problem-Based+Learning%22">Problem-Based Learning*</searchLink>/<searchLink fieldCode="MM" term="%22Problem-Based+Learning+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Education%2C+Medical%22">Education, Medical*</searchLink>/<searchLink fieldCode="MM" term="%22Education%2C+Medical+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Kidney+Neoplasms%22">Kidney Neoplasms*</searchLink>/<searchLink fieldCode="MM" term="%22Kidney+Neoplasms+diagnosis%22">diagnosis</searchLink> <br /><searchLink fieldCode="MM" term="%22Large+Language+Models%22">Large Language Models*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Generative+Artificial+Intelligence%22">Generative Artificial Intelligence</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Large language models (LLMs) are increasingly used in medical education, including in problem-based learning (PBL). Their ability to summarize cases, generate differential diagnoses, and structure discussion raises the question of whether they might eventually replace PBL rather than merely support it. This paper offers a conceptual analysis of that question, using a renal-tumor PBL case derived from recent ChatGPT-assisted teaching research as an illustrative use case. It distinguishes among semantic support, representational uncertainty, and situated uncertainty. LLMs can contribute substantially at the first two levels: they can reformulate cases, identify missing information, keep multiple diagnostic possibilities in play, and suggest coherent next steps. What they do not reproduce is the situated uncertainty through which PBL forms judgment in interaction with peers and tutors. More tools, retrieval, modalities, or sensor input may enrich representation, but they do not by themselves close this gap. The paper therefore argues that LLMs can augment PBL in important ways but do not replace its role in the formation of clinical judgment.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>grounding; large language models; medical education; problem-based learning
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260703 <i>Date Completed: </i>20260703 <i>Latest Revision: </i>20260703
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260703
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3233/SHTI260935
– Name: AN
  Label: PMID
  Group: ID
  Data: 42394097
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42394097
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3233/SHTI260935
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 698
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Generative Artificial Intelligence
        Type: general
      – SubjectFull: Problem-Based Learning methods
        Type: general
      – SubjectFull: Education, Medical methods
        Type: general
      – SubjectFull: Kidney Neoplasms diagnosis
        Type: general
      – SubjectFull: Large Language Models
        Type: general
    Titles:
      – TitleFull: LLMs in Problem-Based Learning: The Grounding Issue.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sariyar M
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 29
              M: 06
              Text: 2026 Jun 29
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1879-8365
          Numbering:
            – Type: volume
              Value: 338
          Titles:
            – TitleFull: Studies in health technology and informatics
              Type: main
ResultId 1