Evaluating hallucinations and repair in open-domain dialogue systems.

dc.contributor.advisorLiesenfeld, A.M.
dc.contributor.advisorThesing, C.
dc.contributor.authorWouw, I. van de
dc.date.issued2023-01-28
dc.description.abstractThis study investigates the repair strategies employed by large language models, during conversations with human interactors and the influence these strategies have on the human interactor’s perception. A corpus of 1123 conversations was collected and analysed, as well as a survey of 14 respondents. The results indicate that the chatbot is limited in its ability to resolve conversational errors and that hallucinations had no adverse influence on user experience. This research has implications for the development of open-domain dialogue systems and conversational agents in the form of evaluation metrics that can be used in order to create a realistic understanding of the capabilities of this technology.
dc.identifier.urihttps://theses.ubn.ru.nl/handle/123456789/15463
dc.language.isoen
dc.thesis.facultyFaculteit der Letteren
dc.thesis.specialisationspecialisations::Faculteit der Letteren::Bachelor Communicatie- en Informatiewetenschappen::International Business Communication
dc.thesis.studyprogrammestudyprogrammes::Faculteit der Letteren::Bachelor Communicatie- en Informatiewetenschappen
dc.thesis.typeBachelor
dc.titleEvaluating hallucinations and repair in open-domain dialogue systems.
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Wouw, Ino van de 1021920-BaThesis.pdf
Size:
898.14 KB
Format:
Adobe Portable Document Format