Achtung: hohPublica wurde am 18.11.2024 aktualisiert. Falls Sie auf Darstellungsfehler stoßen, löschen Sie bitte Ihren Browser-Cache (Strg + Umschalt + Entf). *** Attention: hohPublica was last updated on November 18, 2024. If you encounter display errors, please delete your browser cache (Ctrl + Shift + Del).
 

Knowledge-based and generative-AI-driven pedagogical conversational agents: A comparative study of grice’s cooperative principles and trust

dc.contributor.authorWölfel, Matthias
dc.contributor.authorShirzad, Mehrnoush Barani
dc.contributor.authorReich, Andreas
dc.contributor.authorAnderer, Katharina
dc.date.accessioned2024-09-03T07:30:38Z
dc.date.available2024-09-03T07:30:38Z
dc.date.issued2023de
dc.description.abstractThe emergence of generative language models (GLMs), such as OpenAI’s ChatGPT, is changing the way we communicate with computers and has a major impact on the educational landscape. While GLMs have great potential to support education, their use is not unproblematic, as they suffer from hallucinations and misinformation. In this paper, we investigate how a very limited amount of domain-specific data, from lecture slides and transcripts, can be used to build knowledge-based and generative educational chatbots. We found that knowledge-based chatbots allow full control over the system’s response but lack the verbosity and flexibility of GLMs. The answers provided by GLMs are more trustworthy and offer greater flexibility, but their correctness cannot be guaranteed. Adapting GLMs to domain-specific data trades flexibility for correctness.en
dc.identifier.urihttps://hohpublica.uni-hohenheim.de/handle/123456789/16233
dc.identifier.urihttps://doi.org/10.3390/bdcc8010002
dc.language.isoengde
dc.rights.licensecc_byde
dc.source2504-2289de
dc.sourceBig Data and Cognitive Computing; Vol. 8, No. 1 (2023) 2de
dc.subjectConversational agent
dc.subjectChatbot
dc.subjectEducation
dc.subjectLarge language model
dc.subjectGenerative language model
dc.subjectRetrieval augmented generation
dc.subjectGenerative AI
dc.subjectDigital tutor
dc.subjectDigital assistant
dc.subject.ddc370
dc.titleKnowledge-based and generative-AI-driven pedagogical conversational agents: A comparative study of grice’s cooperative principles and trusten
dc.type.diniArticle
dcterms.bibliographicCitationBig data and cognitive computing, 8 (2024), 1, 2. https://doi.org/10.3390/bdcc8010002. ISSN: 2504-2289
dcterms.bibliographicCitation.issn2504-2289
dcterms.bibliographicCitation.issue1
dcterms.bibliographicCitation.journaltitleBig data and cognitive computing
dcterms.bibliographicCitation.volume8
local.export.bibtex@article{Wölfel2023, url = {https://hohpublica.uni-hohenheim.de/handle/123456789/16233}, doi = {10.3390/bdcc8010002}, author = {Wölfel, Matthias and Shirzad, Mehrnoush Barani and Reich, Andreas et al.}, title = {Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust}, journal = {Big data and cognitive computing}, year = {2023}, volume = {8}, number = {1}, }
local.export.bibtexAuthorWölfel, Matthias and Shirzad, Mehrnoush Barani and Reich, Andreas et al.
local.export.bibtexKeyWölfel2023
local.export.bibtexType@article

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
BDCC-08-00002.pdf
Size:
724.18 KB
Format:
Adobe Portable Document Format