Student Thesis Supervision | Michael Färber's Research Group

We supervise student theses with a research-first, publication-oriented mindset. The current topics are described (incl. contact person) on the linked ScaDS.AI pages below.

Student-led papers (selected):

SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation — CIKM 2025 (demo) · students: Ines Besrour (M.Sc.), Jingbo He (M.Sc.) — Multi-agent RAG framework for scientific QA with inline citations and supporting evidence.
ComplexTempQA: A 100m Dataset for Complex Temporal Question Answering — EMNLP 2025 · students: Raphael Gruber (M.Sc.) — 100M-scale benchmark for complex temporal question answering (Wikipedia/Wikidata).
In-Context Learning for Information Extraction using Fully Synthetic Demonstrations — XLLM@ACL 2025 · students: Ashish Kangen (M.Sc.) — Synthetic demonstration generation + retrieval-based in-context learning for document-level IE.
SimplifyMyText: An LLM-Based System for Inclusive Plain Language Text Simplification — ECIR 2025 · students: Kyuri Im (M.Sc.) — LLM-based system for plain-language simplification with configurable audiences and input formats.

Open artifacts (selected):

SQuAI (code) — Code · students: Ines Besrour (M.Sc.), Jingbo He (M.Sc.) — Multi-agent RAG system for scientific QA with citations.
SQuAI (demo) — Demo · students: Ines Besrour (M.Sc.), Jingbo He (M.Sc.) — Interactive demo of scientific QA with traceable sources.
ComplexTempQA (dataset + code) — Dataset · students: Raphael Gruber (M.Sc.) — Repository for the 100M-scale temporal QA benchmark.
CoDy (code) — Code · students: Daniel Gomm (M.Sc.) — Reference implementation for counterfactual explanations on dynamic graphs.

Note: “M.Sc.” / “B.Sc.” indicate the student level at the time of the work.

More examples: /student-outcomes/

How we work (publication mindset, expectations): /how-we-work/.

Quick answers: /faq/.

No.	Topic	Field(s)	Contact
1	LLM-Augmented Knowledge Graph Search & Question Answering with MCP Servers on SemOpenAlex	Scholarly LLMs, RAG/QA, Knowledge Graphs	Michael Färber; A F M Mohimenul Joaa
2	Transforming Court Decisions into Plain Language with Generative AI	NLP, Text Simplification, Legal AI	Michael Färber
3	Advanced Multimodal Learning for Electronic Health Records: Toward Comprehensive and Interpretable Clinical Intelligence	Multimodal ML, Health / EHR	Zhan Qu
4	LLMs for Scientific Discovery: Designing AI Systems That Generate New Scientific Theories	Scholarly LLMs, Scientific Discovery	Michael Färber
5	Building Creative Large Language Models	LLMs, Generative AI	Michael Färber
6	AI-Moderated Political Debates: Simulating Democratic Discourse with Multi-Agent LLM Systems	Multi-agent LLMs, NLP	Michael Färber
7	Detecting and Mitigating Hate Speech with Large Language Models: Evaluating Strategies and Ethical Considerations	LLMs, Safety, Ethics	Shuzhou Yuan
8	GPT-3, BERT & Co.: When to use which language model?	LLMs, NLP, Evaluation	Michael Färber
9	Using Quantum Computing in Natural Language Processing	Quantum Computing, NLP	Michael Färber
10	Fusing RDF Knowledge Graphs with Deep Learning for Advanced Recommender Systems	Knowledge Graphs (RDF), Graph ML	Michael Färber
11	Extending the RDF Knowledge Graph SemOpenAlex.org	Knowledge Graphs (RDF), SemOpenAlex	Michael Färber
12	Stock Market Predictions through Deep Learning	Machine Learning, Finance	Michael Färber

Important (how to apply):
Please choose a topic and email the listed contact person. To keep the process efficient, please include:

short CV
transcript of records (and, if applicable: transcript of your bachelor’s)
short statement (a few sentences) highlighting your skills, motivation for the topic, and your planned thesis starting date
if applicable: PDF of your bachelor’s thesis
optional but helpful: GitHub/portfolio or a pointer to relevant past projects

We are also open to supervising highly motivated students from other German universities (and international students). Please ensure that any formal requirements (e.g., examiner requirements) are clarified with your home institution.

Back to vacancies