LLM-Based Personalized Learning System in Information Management

Thesis (BA/MA)

Advisor(s): Alisa Mehler (alisa.mehler(at)tum.de)

CONTEXT

In the context of digital education and lifelong learning, personalization has become a key success factor for effective knowledge acquisition. Traditional textbooks, while providing structured and comprehensive information, are typically designed for a broad audience and follow a fixed linear progression. However, learners differ significantly in terms of prior knowledge, professional roles, learning goals, available time, and preferred depth of understanding.

Recent advances in large language models (LLMs) offer new opportunities to transform static learning materials into individualized, interactive learning experiences. Instead of consuming content in a one-size-fits-all manner, learners could be guided through adaptive learning paths that dynamically adjust to their needs, provide interactive explanations, and generate formative assessments such as quizzes or exercises.

Therefore, this thesis investigates the technical and conceptual feasibility of transforming a textbook into personalized learning journeys using LLMs. As a concrete use case, the prototype will be implemented based on the textbook Informationsmanagement by Krcmar (2015). The content will be modularized and used as the foundation for generating individualized, interactive learning paths. The goal is to design and implement an LLM-based system that demonstrates how textbook knowledge can be restructured into adaptive learning sequences with interactive formats and basic feedback-driven personalization.

This thesis develops a prototype that demonstrates the technical and conceptual feasibility of transforming a textbook (Krcmar, 2015) into individualized, interactive learning paths using LLMs.

Examplary Features:

• Learner profiling (role, learning goals, time budget, depth)
• Modular representation of textbook content
• Automatic learning path generation
• LLM-generated interactive content formats (explanations, summaries, quizzes)

• Basic adaptivity based on learner feedback and quiz results

   

TASK(S)

The specific tasks of this thesis may be adapted depending on the thematic focus and research direction. The following list provides an initial selection of potential activities:

• Review relevant literature and existing research on personalized and adaptive learning systems
• Benchmark current platforms and approaches for personalized digital learning
• Analyze practical requirements and design principles for individualized learning environments
• Design a modular representation of the Krcmar (2015) textbook content suitable for LLM-based processing
• Develop and implement an LLM-powered prototype for automatic learning path generation
• Integrate interactive learning elements such as summaries, explanations, and quizzes
• Discuss implications for AI-based learning systems and future educational practices

 

REQUIREMENTS

• High degree of autonomy and individual responsibility
• Strong interest in current IS topics, particularly AI and information management
• Experience with Python and willingness to implement prototypical systems
• Interest in conducting scientific studies and analyzing qualitative and quantitative data

• Structured, reliable, and self-motivated work style

   

FURTHER INFORMATION

The thesis can be written in English or German. The topic can also be adapted to your interests. If you have further questions, please do not hesitate to contact me directly. Please send your application including our specific application form, a current transcript of records and your CV to alisa.mehler(at)tum.de. Please also note that we can only consider applications with complete documents.