DBIS

Information about Diploma/Master thesis process

Open Theses

Running Theses

• From Triples to Pixels: Visual Knowledge Graph Encoding for Knowledge-Augmented Multiple-Choice Question Answering

  ---

  Knowledge-augmented multiple-choice question answering (MCQA) aims to improve robustness and factual grounding by integrating external structured knowledge (e.g., knowledge graphs) into language-model-based decision making. Current high-performing systems typically retrieve a local subgraph relevant to a question and candidate answers, then combine pretrained language representations with explicit graph reasoning modules. This thesis investigates an alternative representation path: ...

• A Rule-Based Agent for Semantic Matching Graph Visualization

  ---

  A Rule-Based Agent for Semantic Matching Graph Visualization

• Resource-Efficient Cyber Risk and Criticality Assessment for Small Power Grid Operators: A Reproducible Algorithm for Deriving Security Requirements and Prioritized Mitigation Plans

  ---

  Power grids are increasingly operated through tightly interconnected IT/OT infrastructures, which raises the attack surface and makes smaller operators with limited resources particularly vulnerable to security-relevant incidents. This thesis develops and evaluates a reproducible, resource-efficient analysis algorithm that captures essential system, process, role, location, and information-flow data to derive protection needs and criticality, and to ...

• Using LLMs with Knowledge Graphs to Enhance Code Generation

  ---

  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation : Lack of access to existing codebases Limited knowledge of project-specific packages, dependencies, and interfaces Difficulty maintaining consistency with established code patterns and architectures To address these challenges, Retrieval Augmented Generation (RAG) approaches have emerged, ...

• Deep Table-Structure Integration for LLM-based Semantic Table Understanding

  ---

  This thesis investigates how Large Language Models (LLMs) can be equipped with a deeper, architecture-level understanding of tabular data, going beyond “tables-as-serialized-text” toward tables-as-structured objects that expose row/column topology, header semantics, cell neighborhoods, and inter-cell dependencies to the model in a principled way . The target setting is Semantic Table Interpretation (STI) as studied in the SemTab challenge, focusing on three ...

View all running theses

Completed Theses

• Federated Machine Learning Architecture for an MDF Production Industry Use Case

  ---

  Federated Machine Learning Architecture for an MDF Production Industry Use Case

• Data-driven quality assurance in grinding manufacturing technology

  ---

  Data-driven quality assurance in grinding manufacturing technology

• A Privacy-Preserving Machine Learning Approach for DGA Detection

  ---

• LLM-Powered Virtual Reality Agents as Technical Support

  ---

  Technical support is an essential aspect of various industries, e.g., to provide help with maintaining machinery and IT systems. However, diagnosing error messages and faults in complex technologies can be a time-consuming and challenging task. The maintainer has to search through the long documentation booklets for the technology in order to find a solution or ...

• Enhancing Mixed Reality Instructional Agents with Large Language Models

  ---

  The innovative integration of Mixed Reality and Large Language Models can lead to highly interactive instructional MR agents. Utilized as automated instructors, these MR agents have the potential to significantly enhance traditional instruction manuals by providing visual guidance. For instance, they can illustrate the next required actions in practical tasks such as tightening screws in ...

View all completed theses