Zobrazit v EDS

Evaluating simulated teaching audio for teacher trainees using RAG and local LLMs

Uloženo v:
Podrobná bibliografie
Název: Evaluating simulated teaching audio for teacher trainees using RAG and local LLMs
Autoři: Ke Fang, Ci Tang, Jing Wang
Zdroj: Sci Rep
Scientific Reports, Vol 15, Iss 1, Pp 1-11 (2025)
Informace o vydavateli: Springer Science and Business Media LLC, 2025.
Rok vydání: 2025
Témata: Teacher student training, Science, RAG framework, Medicine, Simulated teaching, LLMs, Open-source tools, Article
Popis: In the training of teacher students, simulated teaching is a key method for enhancing teaching skills. However, traditional evaluations of simulated teaching typically rely on direct teacher involvement and guidance, increasing teachers’ workload and limiting the opportunities for teacher students to practice independently. This paper introduces a Retrieval-Augmented Generation (RAG) framework constructed using various open-source tools (such as FastChat for model inference and Whisper for speech-to-text) combined with a local large language model (LLM) for audio analysis of simulated teaching. We then selected three leading 7B-parameter open-source Chinese LLMs from the ModelScope community to analyze their generalizability and adaptability in simulated teaching voice evaluation tasks. The results show that the internlm2 model more effectively analyzes teacher students’ teaching audio, providing key educational feedback. Finally, we conducted a system analysis of the simulated teaching of 10 participants in a teaching ability competition and invited three experts to score manually, verifying the system’s application potential. This research demonstrates a potential approach to improving educational evaluation methods using advanced language technology.
Druh dokumentu: Article
Other literature type
Jazyk: English
ISSN: 2045-2322
DOI: 10.1038/s41598-025-87898-5
Přístupová URL adresa: https://doaj.org/article/c31f4dc8ddb74c748ee0943370ffef1b
Rights: CC BY NC ND
Přístupové číslo: edsair.doi.dedup.....24fbfbec395a37e057ce4d09c4e1f9e4
Databáze: OpenAIRE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://explore.openaire.eu/search/publication?articleId=doi_dedup___%3A%3A24fbfbec395a37e057ce4d09c4e1f9e4
    Name: EDS - OpenAIRE (s4221598)
    Category: fullText
    Text: View record at OpenAIRE
  – Url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=search&db=pmc&term=2045-2322[TA]+AND+[PG]+AND+2025[PDAT]
    Name: FREE - PubMed Central (ISSN based link)
    Category: fullText
    Text: Full Text
    Icon: https://imageserver.ebscohost.com/NetImages/iconPdf.gif
    MouseOverText: Check this PubMed for the article full text.
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsair&genre=article&issn=20452322&ISBN=&volume=15&issue=&date=20250129&spage=&pages=&title=Scientific Reports&atitle=Evaluating%20simulated%20teaching%20audio%20for%20teacher%20trainees%20using%20RAG%20and%20local%20LLMs&aulast=Ke%20Fang&id=DOI:10.1038/s41598-025-87898-5
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Fang%20K
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsair
DbLabel: OpenAIRE
An: edsair.doi.dedup.....24fbfbec395a37e057ce4d09c4e1f9e4
RelevancyScore: 965
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 964.739440917969
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Evaluating simulated teaching audio for teacher trainees using RAG and local LLMs
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Ke+Fang%22">Ke Fang</searchLink><br /><searchLink fieldCode="AR" term="%22Ci+Tang%22">Ci Tang</searchLink><br /><searchLink fieldCode="AR" term="%22Jing+Wang%22">Jing Wang</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Sci Rep<br />Scientific Reports, Vol 15, Iss 1, Pp 1-11 (2025)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Springer Science and Business Media LLC, 2025.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Teacher+student+training%22">Teacher student training</searchLink><br /><searchLink fieldCode="DE" term="%22Science%22">Science</searchLink><br /><searchLink fieldCode="DE" term="%22RAG+framework%22">RAG framework</searchLink><br /><searchLink fieldCode="DE" term="%22Medicine%22">Medicine</searchLink><br /><searchLink fieldCode="DE" term="%22Simulated+teaching%22">Simulated teaching</searchLink><br /><searchLink fieldCode="DE" term="%22LLMs%22">LLMs</searchLink><br /><searchLink fieldCode="DE" term="%22Open-source+tools%22">Open-source tools</searchLink><br /><searchLink fieldCode="DE" term="%22Article%22">Article</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: In the training of teacher students, simulated teaching is a key method for enhancing teaching skills. However, traditional evaluations of simulated teaching typically rely on direct teacher involvement and guidance, increasing teachers’ workload and limiting the opportunities for teacher students to practice independently. This paper introduces a Retrieval-Augmented Generation (RAG) framework constructed using various open-source tools (such as FastChat for model inference and Whisper for speech-to-text) combined with a local large language model (LLM) for audio analysis of simulated teaching. We then selected three leading 7B-parameter open-source Chinese LLMs from the ModelScope community to analyze their generalizability and adaptability in simulated teaching voice evaluation tasks. The results show that the internlm2 model more effectively analyzes teacher students’ teaching audio, providing key educational feedback. Finally, we conducted a system analysis of the simulated teaching of 10 participants in a teaching ability competition and invited three experts to score manually, verifying the system’s application potential. This research demonstrates a potential approach to improving educational evaluation methods using advanced language technology.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Article<br />Other literature type
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2045-2322
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1038/s41598-025-87898-5
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/c31f4dc8ddb74c748ee0943370ffef1b" linkWindow="_blank">https://doaj.org/article/c31f4dc8ddb74c748ee0943370ffef1b</link>
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: CC BY NC ND
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsair.doi.dedup.....24fbfbec395a37e057ce4d09c4e1f9e4
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsair&AN=edsair.doi.dedup.....24fbfbec395a37e057ce4d09c4e1f9e4
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1038/s41598-025-87898-5
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Teacher student training
        Type: general
      – SubjectFull: Science
        Type: general
      – SubjectFull: RAG framework
        Type: general
      – SubjectFull: Medicine
        Type: general
      – SubjectFull: Simulated teaching
        Type: general
      – SubjectFull: LLMs
        Type: general
      – SubjectFull: Open-source tools
        Type: general
      – SubjectFull: Article
        Type: general
    Titles:
      – TitleFull: Evaluating simulated teaching audio for teacher trainees using RAG and local LLMs
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Ke Fang
      – PersonEntity:
          Name:
            NameFull: Ci Tang
      – PersonEntity:
          Name:
            NameFull: Jing Wang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 29
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 20452322
            – Type: issn-locals
              Value: edsair
            – Type: issn-locals
              Value: edsairFT
          Numbering:
            – Type: volume
              Value: 15
          Titles:
            – TitleFull: Scientific Reports
              Type: main
ResultId 1