Master Thesis with 3DSE Management Consultants.
📌 Key facts
- 📌 Key facts
- 💡 Background
- 🦾Who We Are
- 🎯 Goals
- 🎓 Profile
- 📚 Further Reading
- ➕ Additional Information
- 📝 How to Apply
- 📬 Contact
💡 Background
R&D knowledge is distributed across requirements, tests, product structures, simulations, customer feedback, and technical documentation. LLMs and conventional RAG can make this information easier to access, but may struggle with traceability and relationships across engineering artefacts. Ontologies and knowledge graphs make those relationships explicit, though they require effort to build and maintain. The key question is where they create enough measurable value to justify that effort.
🦾Who We Are
3DSE Management Consultants is a specialized management consultancy focused on product and service development. We help industrial companies make their development organizations more effective by improving strategy, processes, structures, and collaboration. Our work combines rigorous methods with a strong focus on people and behavior to turn complex challenges into measurable results.
The Chair for Strategy and Organization is focused on research with impact. This means we do not want to repeat old ideas and base our research solely on the research people did 10 years ago. Instead, we currently research topics that will shape the future. Topics such as Agile Organisations and Digital Disruption, Blockchain Technology, Creativity and Innovation, Digital Transformation and Business Model Innovation, Diversity, Education: Education Technology and Performance Management, HRTech, Leadership, and Teams.. We are always early in noticing trends, technologies, strategies, and organisations that shape the future, which has its ups and downs.
🎯 Goals
Evaluate when ontology- or knowledge-graph-enhanced LLM applications improve the quality, traceability, and reliability of R&D work compared with direct LLM use and conventional RAG.
Research question: Which R&D tasks benefit from graph-based approaches, and do the benefits justify their additional implementation and maintenance effort?
🎓 Profile
Suitable for students in information systems, computer science, data science, AI, industrial engineering, software engineering, or a related field. Applicants should bring strong analytical skills, an interest in LLMs and knowledge management, and experience with Python or data processing. Familiarity with RAG, databases, knowledge graphs, or experimental evaluation is an advantage.
📚 Further Reading
- Lewis et al. (2020), “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.”
- Pan et al. (2023), “Unifying Large Language Models and Knowledge Graphs: A Roadmap.”
- Edge et al. (2024), “From Local to Global: A Graph RAG Approach to Query-Focused Summarization.”
- Han et al. (2025), “RAG vs. GraphRAG: A Systematic Evaluation and Key Insights.”
➕ Additional Information
The thesis will compare three prototypes: direct LLM use, conventional document- or vector-based RAG, and graph-enhanced RAG. They will be tested on shared R&D tasks and data. Evaluation may cover answer correctness, source traceability, hallucinations, information coverage, multi-step reasoning, runtime, user acceptance, and cost. Possible tasks include checking requirements for inconsistencies, linking defects to product components, and deriving tests from customer feedback.
📝 How to Apply
Email the thesis title you are interested in and a short introduction to your background and research interests.
📬 Contact
Prof. Dr. Clemens van Dinther
3DSE Management Consultants GmbH