Chair: Prof. Dr.-Ing. Michael Färber
E-Mail: michael.faerber@tu-dresden.de
Office: Strehlener Str. 12-14, Room 733, 01069 Dresden (Google Maps)
Secretary: Thomas Bruderrek
Phone: +49 (0)351 463 40900 (Secretary)

Recent News

• 09/2025: Three papers have been accepted at EMNLP 2025 ! See you in Suzhou, China!
• 08/2025: I gave a keynote on “LLMs and Knowledge Graphs for Science: From Papers to Insights” at Semantics 2025.
• 05/2025: Two papers have been accepted at KDD 2025: PathToCausality/KGSubgraphAsPrompt in the Research Track and Explainable-GraphNeuralVortexDetection in the Applied Data Science Track! Additionally, our CoDy paper is accepted to ICML’25. See you in Canada!
• 06/2024: Ember has been accepted to EMNLP 2024 as a main conference paper! Additionally, 2 Papers (AutoRDF2GML + KGPrompt) accepted at ISWC’24. See you in Baltimore!
• 05/2024: Paper GNNavi accepted at Findings of ACL’24. See you in Bangkok!
• 04/2024: Starting as full professor (W3) at ScaDS.AI Dresden/Leipzig / TU Dresden.
• 11/2023: Best Paper Award (1000 USD) for SemOpenAlex at ISWC’23.

Our Group

We focus on AI research that prioritizes trustworthiness and alignment with human values. Particularly, our research lies at the intersection of natural language processing (e.g., LLMs), graph-based machine learning, and structured knowledge representation (e.g., knowledge graphs). For instance, we work on large-scale information extraction and knowledge graph construction, faithful text generation, and learning over graph-structured data. Combining symbolic and neural approaches, we advance scalable AI technologies capable of nuanced language comprehension and structured data analytics over complex real-world data.

Professional Profile

• Since April 2024, W3 Full Professor and head of the research group “Scalable Software Architectures for Data Analytics” at the AI Center ScaDS.AI Dresden/Leipzig at TUD Dresden University of Technology (appointed at age 36).
• From 2020 to 2024, Deputy Full Professor (“W3-Vertretungsprofessor”) for Web Science at the Institute AIFB of the Karlsruhe Institute of Technology (KIT, Germany), leading a team of 7 PhD students, 1 KIT junior research group leader, and 1 postdoc.
• Research in AI, particularly at the intersection of natural language processing (LLMs!), machine learning (GNNs!), and knowledge representation (KGs!).
• 100+ publications at highly-ranked conferences (e.g., ACL, EMNLP, KDD, CIKM, ISWC, ECIR, ICML, NAACL) and journals (e.g., SWJ, IJDL, Scientometrics) with international researchers as co-authors.
• Princial Investigator (PI) in several projects (e.g., ChemKB, IIDI, KIGLIS, KIWI, TruthfulLM) and multi-million third-party funding.
• Many years of teaching experience: Lectures with up to 600 students, receiving Faculty award.
• Understanding of interdisciplinary research topics based on parallel studies in philosophy (B.A.).

Introduction and Research Spotlight

Online Demo Systems

• SQuAI: Scientific Question Answering with Multi-Agent RAG.
• Klartext: SimplifyMyText: KI-basierte Übersetzung von Webseiten in einfache Sprache.
• RefBee: Tracks publications across bibliographic databases.
• C-Rex: Recommends citations for texts.
• PaperHunter: Searches citation contexts in papers.
• ScholarSight: Explores scientific concept trends.
• Linked Crunchbase: Queries startup and innovation data in RDF format.

Data Sets

• SemOpenAlex: A massive knowledge graph about publications, authors, etc.
• LPWC: Linked Papers With Code is an RDF KG that models nearly 400,000 machine learning papers, capturing tasks, datasets, methods, evaluations, and results.
• DSKG: A knowledge graph of datasets.
• unarXive: Contains annotated full texts from arXive.org.
• Microsoft Academic Knowledge Graph: Metadata of publications across disciplines.
• FAIRnets: Metadata about neural networks.

Projects

• LLM4Edu: Learning Large Language Models on Graphs for Education
• Klartext: AI-based Translation of Websites Into Plain Language

Open Student Positions and Theses

… please ask. See complete list here

• GPT-3, BERT & Co.: When to use which language model?
• Using Quantum Computing in Natural Language Processing
• Alles nur Show? Ein automatischer Vergleich von Nachrichten vor der Bundestagswahl mit dem Koalitionsvertrag mittels Natural Language Processing
• Creating a Dataset of Textual Descriptions of Planned Actions and Expectations of Entities
• Creating a Multimodal Dataset of Actions Labeled with their Expected Durations
• Creating a Dataset of Complex Temporal Questions for Testing Large Language Models (LLMs)
• Advanced Multi-Modality Learning in Electronic Health Records for Personalized Medical Recommendations
• Fusing RDF Knowledge Graphs with Deep Learning for Advanced Recommender Systems
• Extending the RDF Knowledge Graph SemOpenAlex.org
• Large Language Model-enhanced Graph Message Passing Network for Link Prediction
• Stock Market Predictions through Deep Learning
• Designing and Executing a Large-Scale User Study on Scientific Text Simplification

and here.

_{Prof. Dr.-Ing. Michael Färber has supervised over 50 Bachelor and Master theses and encourages both English and German-speaking students to apply. Many thesis topics are available for study abroad through partner institutions and DAAD funding, all with the goal of co-authoring a scientific paper based on the thesis.}

Online Presence

• Personal – Research Group Website (frequently updated)
• Google Scholar
• DBLP
• Wikidata (Scholia, Reasonator)
• ORCID
• ResearchGate
• Semantic Scholar
• YouTube