Enhancing chatbot-assisted study program orientation


Dieing, Thilo I. ; Scheffler, Marc ; Cohausz, Lea


[img] PDF
Workshop_Chatbot.pdf - Accepted

Download (351kB)

DOI: https://doi.org/10.18420/delfi2024-ws-32
URL: https://dl.gi.de/items/2639a4e5-fde7-450e-ad22-e6c...
URN: urn:nbn:de:bsz:180-madoc-678551
Document Type: Conference or workshop publication
Year of publication: 2024
Book title: Workshopband der 22. Fachtagung Bildungstechnologien (DELFI) : 09.09.-11.09.2024, Fulda, Deutschland
Page range: 223-232
Conference title: EduRS 2024 - Recommender Systems in Education, Workshop bei der DELFI 2024, 23. Fachtagung Bildungstechnologien (DELFI)
Location of the conference venue: Fulda, Germany
Date of the conference: 09.09.24
Publisher: Kiesler, Natalie ; Schulz, Sandra
Place of publication: Bonn
Publishing house: Gesellschaft für Informatik (GI)
Related URLs:
Publication language: English
Institution: School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
License: CC BY 4.0 Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject: 004 Computer science, internet
Keywords (English): chatbot , study program recommendation , LLM , RAG , CASPO
Abstract: As university dropout rates increase, implementing innovative solutions is crucial to reduce attrition. Aligning students’ interests with their study programs enhances academic success, satisfaction, and retention. This paper presents a novel approach using open-source Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) to develop a semi-open-domain knowledge chatbot. The chatbot generates informed responses and recommendations to diverse student queries by retrieving relevant data while maintaining ethical standards and avoiding biased responses. When testing five model combinations on 70 prompts partially from real study advisors, results demonstrate that the RAG approach with the Mixtral LLM and RoBERTa embedding model offers superior performance. Our method for handling critical user prompts further indicates a significantly improved response quality. These findings advance service-oriented chatbots in education, aiming to reduce student attrition through accurate and helpful program recommendations.


SDG 4: Quality Education


Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.




Metadata export


Citation


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item