2513607 – Seminar Knowledge Graphs and Large Language Models (Master)

Allgemeine Informationen

Wichtige Informationen

Large Language Models (LLMs) have evolved into powerful AI systems capable of generating content, supporting complex reasoning, and interacting with external tools and environments. Recent developments extend these capabilities beyond text, enabling multimodal processing and the emergence of autonomous, agent-like systems that can plan and execute tasks over multiple steps. Despite this progress, key limitations persist. LLMs often produce unverified or incorrect information, lack transparency in their decision-making processes, and struggle to consistently incorporate domain-specific knowledge. These challenges highlight the need for methods that improve reliability, interpretability, and knowledge grounding. Knowledge Graphs (KGs) offer structured and semantically rich representations of information, capturing entities, relationships, and domain constraints. Their integration with LLMs provides a complementary approach: while LLMs excel at language understanding and generation, KGs contribute explicit knowledge, reasoning capabilities, and explainable structures.

This seminar explores recent advances at the intersection of LLMs and Knowledge Graphs, with a particular focus on emerging directions such as hybrid AI systems and knowledge-aware agents, covering areas of interest including, but not limited to:

- Completion and construction of KGs using LLMs
- Question answering with KGs and LLMs
- Retrieval-augmented methods with structured and unstructured data
- Explainability of LLMs with KG integration
- Reasoning with LLMs and KGs
- Enhanced prompt engineering using KGs
- Use of KGs for memory, planning, and tool integration in AI systems


The research papers chosen for the presentations are published in reputable venues such as EMNLP, IJCAI, ACL, etc. The goal of the seminar is to understand the allotted paper and other related literature and present the paper. The students are required to submit a 15-page report, with 10 pages of main content (excluding references and the appendix). Also, the students need to reimplement the code provided by the corresponding authors of the papers and produce results on existing datasets.

Contributions of the students: each student will be assigned one paper on the topic, which could be a research paper discussing a novel approach or a resource paper presenting datasets, tools, etc. The student will be responsible for the following tasks:

1. Report Writing
- Read the assigned paper thoroughly and write a 15-page seminar report explaining the methods and findings in their own words.
2. Presenting
- Prepare and deliver a seminar presentation to share insights from the paper with other seminar participants.
3. Conducting Experiments:
- If the authors provide code, re-implement it for small-scale experiments using Google Colab or make the implementation available via GitHub.

The seminar will be limited to 10 participants.

Tutor Team:

Dr. Genet Asefa Gesese
Dr. Dilek Yargan
M. Sc. Rafael Patronilo
M. Sc. Amel Gader

The kick-off meeting will take place on Wednesday, April 29, 2026 at 14:00 - 15:30 in room 5A-09 (AIFB building)

Allgemein

Sprache

Englisch

Lizenz und Nachnutzung

Lizenz

All rights reserved

Verfügbarkeit

Zugriff

28. Apr 2026, 16:00 - 31. Jul 2026, 17:00

Aufnahmeverfahren

Sie können diesem Kurs direkt beitreten.

Zeitraum für Beitritte

Unbegrenzt

Für Kursadministration freigegebene Daten

Daten des Persönlichen Profils

Anmeldename
Vorname
Nachname
E-Mail
Matrikelnummer

Zusätzliche Informationen

Objekt-ID

3876274