LLMs for Data Integration, Knowledge Graphs & Compliance Assessment – Master Thesis Projects in NorwAI

Today’s data landscape spans industry, smart cities, digital services, and environmental systems. Unlocking its potential demands advanced techniques for data integration, knowledge graphs, and responsible AI.

In the Norwegian Research Center for AI Innovation (NorwAI), students can work with leading industry partners to explore how LLMs can transform data interoperability and enable automated compliance assessment in real‑world data and AI systems.

Supervision

Master’s theses in the NorwAI DATA work package are supervised jointly by SINTEF Digital and a university supervisor.

• Students from NTNU or any other university are welcome.
• For NTNU students: an NTNU supervisor is required for formal academic registration, while SINTEF provides most of the practical supervision.
• For students from other universities: the thesis can be carried out under the student’s home‑institution supervisor, with SINTEF collaborating closely throughout the project.

Master Thesis Projects

For more information about specific topics please visit the following pages:

1. LLM‑Based Compliance Assessment with LexAlign: Telenor’s Anomaly‑Detection Pipeline

The goal of the thesis is to (1) explore how Large Language Models (LLMs) and LexAlign can be used to assess GDPR and EU AI Act compliance for Telenor’s anomaly‑detection pipeline; and (2) extend LexAlign to support company-specific or sector-specific for the telecom sector.

2. AI symbolic for enhancing reasoning and trustworthiness of GPT

The goal of this thesis is to explore the use of symbolic AI (e.g., knowledge graphs) to enhance reasoning capabilities of GPT and reduce hallucinations and opaqueness, and improve trustworthiness.

3. Applying ChatGPT for Data Integration

The goal of the thesis is to explore the applicability of ChatGPT to enable a higher degree of automation for data integration in real national and European industrial/research projects.

4. Enhancing Data Harmonization with LLMs

The goal of this thesis is to explore the use of Large Language Models (LLMs) to enhance data harmonization related to Knowledge Graphs (KGs).

5. Digital System Models – Implementation and application

The goal of this thesis is to (a) reduce implementation costs of building digital system models using deep learning and semantic technologies, and (b) ensure digital systems models enable domain experts (e.g., engineers and researchers) to better monitor and optimize the performances of real complex systems such as energy production facilities and energy grid infrastructures.

6. GeoAI for Environmental Twins 

The goal of this thesis is to implement various GeoAI solutions for specific problem areas such as (1) curation and quality management of geospatial data, (2) automated annotation in geospatial data, and (3) automate analytics workflows.