Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Large Language Models as Domain-independent Dialogue Component for Intelligent Tutoring Systems – Teaching Concepts of SQL

Publication

Large Language Models as Domain-independent Dialogue Component for Intelligent Tutoring Systems – Teaching Concepts of SQL

Voelker, Adrian; Thaler, Anna Magdalena; Summerer, Maximilian T.; u. a. (2025): Large Language Models as Domain-independent Dialogue Component for Intelligent Tutoring Systems – Teaching Concepts of SQL, in: Ute Schmid, Jochen L. Leidner, Michael Kohlhase, u. a. (Hrsg.), Proceedings of the Second Work shop on Artificial Intelligence for Artificial Intelligence Education (AI4AI Learning 2024), Bamberg: University of Bamberg Press, S. 33–48, doi: 10.20378/irb-108886.

Details

Faculty/Chair
Faculty/Professorship
Author
Voelker, Adrian
Thaler, Anna Magdalena
Summerer, Maximilian T.
Title of the compilation
Proceedings of the Second Work shop on Artificial Intelligence for Artificial Intelligence Education (AI4AI Learning 2024)
Editors
Leidner, Jochen L.
Kohlhase, Michael
Wolter, Diedrich
Conference
Second Workshop on Artificial Intelligence for Artificial Intelligence Education (AI4AI Learning 2024), Würzburg
Publisher Information
University of Bamberg Press : Bamberg
Year of publication
2025
ISBN
978-3-98989-054-1
Language
English
DOI
Licence
Abstract

With the advance of generative pre-trained language models, new opportunities arise for domain-independent dialogue-based instruction in the context of intelligent tutoring systems (ITS). We propose an approach for combining large language models (LLMs) with domain-specific knowledge graphs to take advantage of the performance of LLMs in natural language processing tasks while still ensuring a faithful knowledge base. We present a prototypical implementation of an ITS for the structured query language SQL to explore the potential of combining LLM and domain specific knowledge graphs for dialogue based didactic intervention. While learning a programming language relies on both declarative knowledge about the language concepts and procedural knowledge for writing program code with respect to a specific task, in this paper we focus on ITS support for acquisition of declarative knowledge. In our implementation LLMs are employed for semantic parsing relating student’s

questions to the addressed knowledge elements of the domain model as well as for feedback formulation based on retrieved information from the knowledge graph. Likewise, knowledge diagnosis is realized by semantic parsing of student answers and mapping them against the LLM output. We conducted a first exploratory evaluation using the LLM Mixtral 8x7B Instruct in combination with our SQL knowledge graph. Exploring different prompting strategies, the best strategy resulted in 90% correct diagnosis of student answers.

GND Keywords
Intelligentes Tutorsystem
Großes Sprachmodell
Wissensgraph
SQL
Deklaratives Wissen
Keywords
Intelligent Tutoring Systems
Large Language Models
Knowledge Graphs
SQL
Declarative Knowledge
DDC Classification
004 Computer science
RVK Classification
ST 302
Type
Conferenceobject
URI
Activation date
2025-07-11

Permalink: https://fis.uni-bamberg.de/handle/uniba/108886 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.