Publikation: Regaining Control : Enabling Educators to Build Specialized AI Chat Bots with Retrieval Augmented Generation
Lade...
Dateien
Datum
2025
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Institutionen der Bundesrepublik Deutschland: 01JA23M02K
Projekt
MINT-Pro-NED
Open Access-Veröffentlichung
Open Access Bookpart
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
DU BOULAY, Benedict, Hrsg., Tania DI MASCIO, Hrsg., Edmundo TOVAR, Hrsg. und andere. Proceedings of the 17th International Conference on Computer Supported Education. Volume 2: CSEDU. Setúbal, Portugal: Scitepress, 2025, S. 371-378. ISSN 2184-5026. ISBN 978-989-758-746-7. Verfügbar unter: doi: 10.5220/0013425500003932
Zusammenfassung
Conversational AI (chat) bots are powerful and helpful tools, but are not suited for the unrestricted use in many classrooms: They may hallucinate, easily veer from the topic of instruction, and are vulnerable to malicious prompting. Retrieval-augmented generation (RAG) is a technique that allows educators to constrain chat bots to a specific area of expertise, reducing hallucinations and vulnerability to mis-use. We are working on a low-code solution that enables tech-savvy educators to build such a RAG-based chat bot system themselves, thus retaining full control over the content and behavior of their bot. We present the first version of this system and promising initial feedback from educators and students on its suitability, reliability and flexibility.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Retrieval-Augmented Generation, Large Language Models, Education
Konferenz
17th International Conference on Computer Supported Education, 1. Apr. 2025 - 3. Apr. 2025, Porto, Portugal
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
PAMPEL, Barbara, Simon MARTIN, Ulrike PADÓ, 2025. Regaining Control : Enabling Educators to Build Specialized AI Chat Bots with Retrieval Augmented Generation. 17th International Conference on Computer Supported Education. Porto, Portugal, 1. Apr. 2025 - 3. Apr. 2025. In: DU BOULAY, Benedict, Hrsg., Tania DI MASCIO, Hrsg., Edmundo TOVAR, Hrsg. und andere. Proceedings of the 17th International Conference on Computer Supported Education. Volume 2: CSEDU. Setúbal, Portugal: Scitepress, 2025, S. 371-378. ISSN 2184-5026. ISBN 978-989-758-746-7. Verfügbar unter: doi: 10.5220/0013425500003932BibTex
@inproceedings{Pampel2025Regai-73357,
title={Regaining Control : Enabling Educators to Build Specialized AI Chat Bots with Retrieval Augmented Generation},
year={2025},
doi={10.5220/0013425500003932},
isbn={978-989-758-746-7},
issn={2184-5026},
address={Setúbal, Portugal},
publisher={Scitepress},
booktitle={Proceedings of the 17th International Conference on Computer Supported Education. Volume 2: CSEDU},
pages={371--378},
editor={du Boulay, Benedict and Di Mascio, Tania and Tovar, Edmundo},
author={Pampel, Barbara and Martin, Simon and Padó, Ulrike}
}RDF
<rdf:RDF
xmlns:dcterms="http://purl.org/dc/terms/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:bibo="http://purl.org/ontology/bibo/"
xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
xmlns:foaf="http://xmlns.com/foaf/0.1/"
xmlns:void="http://rdfs.org/ns/void#"
xmlns:xsd="http://www.w3.org/2001/XMLSchema#" >
<rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/73357">
<dc:contributor>Padó, Ulrike</dc:contributor>
<dc:creator>Pampel, Barbara</dc:creator>
<dcterms:abstract>Conversational AI (chat) bots are powerful and helpful tools, but are not suited for the unrestricted use in many classrooms: They may hallucinate, easily veer from the topic of instruction, and are vulnerable to malicious prompting. Retrieval-augmented generation (RAG) is a technique that allows educators to constrain chat bots to a specific area of expertise, reducing hallucinations and vulnerability to mis-use. We are working on a low-code solution that enables tech-savvy educators to build such a RAG-based chat bot system themselves, thus retaining full control over the content and behavior of their bot. We present the first version of this system and promising initial feedback from educators and students on its suitability, reliability and flexibility.</dcterms:abstract>
<dc:language>eng</dc:language>
<dcterms:issued>2025</dcterms:issued>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/73357"/>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/73357/4/Pampel_2-ac5l0qrkxfmc9.pdf"/>
<dcterms:title>Regaining Control : Enabling Educators to Build Specialized AI Chat Bots with Retrieval Augmented Generation</dcterms:title>
<dc:contributor>Pampel, Barbara</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2025-05-19T07:53:26Z</dc:date>
<dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/73357/4/Pampel_2-ac5l0qrkxfmc9.pdf"/>
<dc:contributor>Martin, Simon</dc:contributor>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:rights>terms-of-use</dc:rights>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2025-05-19T07:53:26Z</dcterms:available>
<dc:creator>Martin, Simon</dc:creator>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:creator>Padó, Ulrike</dc:creator>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
