Logo des Repositoriums
 

A Multidisciplinary Approach to AI-based self-motivated Learning and Teaching with Large Language Models

dc.contributor.authorRanzenberger, Thomas
dc.contributor.authorFreier, Carolin
dc.contributor.authorReinold, Luca
dc.contributor.authorRiedhammer, Korbinian
dc.contributor.authorSchneider, Fabian
dc.contributor.authorSimic, Christopher
dc.contributor.authorSimon, Claudia
dc.contributor.authorFreisinger, Steffen
dc.contributor.authorGeorges, Munir
dc.contributor.authorBocklet, Tobias
dc.contributor.editorSchulz, Sandra
dc.contributor.editorKiesler, Natalie
dc.date.accessioned2024-09-03T16:26:17Z
dc.date.available2024-09-03T16:26:17Z
dc.date.issued2024
dc.description.abstractWe present a learning experience platform that uses machine learning methods to support students and lecturers in self-motivated online learning and teaching processes. The platform is being developed as an agile open-source collaborative project supported by multiple universities and partners. The development is guided didactically, reviewed, and scientifically evaluated in several cycles. Transparency, data protection and the copyright compliant use of the system is a central part of the project. The system further employs large language models (LLMs). Due to privacy concerns, we utilize locally hosted LLM instances and explicitly do not rely on available cloud products. Students and lecturers can interact with an LLM-based chatbot in the current prototype. The AI-generated outputs contain cross-references to the current educational video’s context, indicating if sections are based on the lectures context or world knowledge. We present the prototype and results of our qualitative evaluation from the perspective of lecturers and students.en
dc.identifier.doi10.18420/delfi2024_11
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/44492
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofProceedings of DELFI 2024
dc.relation.ispartofseriesDELFI
dc.subjectArtificial Intelligence in Education
dc.subjectLearning Experience Platform
dc.subjectOpen Source Software
dc.subjectLarge Language Models
dc.titleA Multidisciplinary Approach to AI-based self-motivated Learning and Teaching with Large Language Modelsen
dc.typeText/Conference paper
mci.conference.date09.-11. September 2024
mci.conference.locationFulda
mci.conference.sessiontitleKI Einsatz in der Hochschule I
mci.document.qualitydigidoc
mci.reference.pages133-140

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
Thomas-Ranzenberger.pdf
Größe:
5.54 MB
Format:
Adobe Portable Document Format