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

Seminar Knowledge Graphs and Large Language Models (Master) 2024/2025 The seminar covers state-of-the-art topics at the intersection of knowledge graphs and large language models (LLMs), focusing on recent advancements and research. The research papers chosen for the presentations are published in reputable venues such as EMNLP, NAACL, 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 10-page report on the paper excluding the references and appendix. Also, the students need to reimplement the code provided by the corresponding authors of the papers and produce results on existing datasets. The seminar will be limited to 10 participants.

Allgemeine Informationen

Wichtige Informationen

The seminar covers state-of-the-art topics at the intersection of knowledge graphs (KGs) and large language models (LLMs), focusing on recent advancements and research. LLMs such as GPT-3 have shown remarkable capabilities in transforming various natural language processing (NLP) tasks across different domains. However, LLMs often generate incorrect answers, known as hallucinations, posing significant challenges to their usability and reliability. Additionally, LLMs operate as black boxes, making it difficult to understand how they arrive at specific conclusions, leading to transparency and explainability issues. Combining LLMs with KGs creates a powerful synergy that significantly enhances the capabilities of artificial intelligence across various tasks. This integration leverages the strengths of both technologies, with LLMs excelling at understanding and generating human-like text, and KGs providing structured, reliable information about entities and their relationships. Together, they offer a robust approach to problem-solving across diverse domains.

This seminar explores a range of cutting-edge topics including, but not limited to:

- KG completion using LLMs
- Question answering with KGs and LLMs
- Explainability of LLMs with KG integration
- Reasoning with LLMs and KGs
- Enhanced prompt engineering using KGs

The research papers chosen for the presentations are published in reputable venues such as EMNLP, NAACL, 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
M. Sc. Mary Ann Tan
M. Sc. Mahsa Vafaie
M. Sc. Ebrahim Norouzi

The kick-off meeting will take place on Wednesday, October 23rd at 14:00 in room 5A-09 (AIFB building)

Zusammenfassung

Seminar Knowledge Graphs and Large Language Models (Master) 2024/2025

The seminar covers state-of-the-art topics at the intersection of knowledge graphs and large language models (LLMs), focusing on recent advancements and research. The research papers chosen for the presentations are published in reputable venues such as EMNLP, NAACL, 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 10-page report on the paper excluding the references and appendix. Also, the students need to reimplement the code provided by the corresponding authors of the papers and produce results on existing datasets.

The seminar will be limited to 10 participants.

Allgemein

Sprache

Englisch

Verfügbarkeit

Zugriff

Unbegrenzt – wenn online geschaltet

Aufnahmeverfahren

Sie können diesem Kurs direkt beitreten.

Zeitraum für Beitritte

Unbegrenzt

Veranstaltungszeitraum

23. Okt 2024 - 19. Mär 2025

Für Kursadministratoren freigegebene Daten

Daten des Persönlichen Profils

Anmeldename
Vorname
Nachname
E-Mail
Matrikelnummer

Zusätzliche Informationen

Objekt-ID

3314779