For Students

Open Thesis Topics

Students who are eager to develop their skills by doing a research-oriented thesis in our group should mail their interests to webis@listserv.uni-weimar.de. Suitable topic candidates are shown in the following list. Your own suggestions for topics are also welcome, for which you can draw inspiration from our recent publications.

  • Personalizing Question Answering

Open Student Assistant Topics

Students who want to improve their skills and work with us can apply for a position as a student assistant at webis@listserv.uni-weimar.de. We are currently looking for assistants to work on the following topics:

  • We currently have no open topics. You can always let us know if you're interested.

Ongoing Theses

  • Halle
    • Building Medical Knowledge Graphs for Knowledge Injection in LLMs (supervised by Alexander Bondarenko and Jan Heinrich Merker)
  • Jena
    • Evaluating Pre-Training Techniques for Single-Vector Encoder Models (supervised by Ferdinand Schlatt)
    • Testing the Limits of Multi-Vector Bi-Encoder Models (supervised by Ferdinand Schlatt)
    • Analyzing the Effectiveness of Community Self-moderation on the Fediverse (supervised by Jan Heinrich Merker and Matti Wiegmann)
    • Large-scale Query Log Analyses (supervised by Jan Heinrich Merker)
    • Dense Boolean Retrieval for Systematic Reviews (supervised by Ferdinand Schlatt)
    • Improving Learned Lexical Retrieval Models by Removing Lexical Dependencies (supervised by Ferdinand Schlatt)
    • Reducing the Size of Dense Retrieval Indexes by Removing Unimportant Terms (supervised by Ferdinand Schlatt)
    • Estimating the Trustworthiness of Wikipedia Articles (supervised by Jan Heinrich Merker and Matthias Hagen)
    • Argument Mining in the AQL (supervised by Ines Zelch)
  • Leipzig
    • Optimizing Prompts for Text-To-Image Generation in Discrete Token Space (supervised by Niklas Deckers)
    • Extracting negated causal statements (supervised by Tim Hagen)
    • Creating the Dataset for the Touché 25 Shared Task: Image Retrieval/Generation for Arguments (supervised by Maximilian Heinrich and Johannes Kiesel)
    • Facets of complexity in scholarly political language (supervised by Magdalena Wolska)
    • Simplifying the language of political argumentation (supervised by Magdalena Wolska)
    • Text2SQL. Exploring Relational Databases with Natural Language User Interfaces (supervised by Tim Gollub)
    • Psychological Features of Argumentation (supervised by Maximilian Heinrich)
    • Lightweight Passage Re-ranking Using Embeddings from Pre-trained Language Models (supervised by Ferdinand Schlatt and Harry Scells)
    • Logical Features of Neural Networks (supervised by Maximilian Heinrich)
    • Classification of Multimodal Social Media Posts (supervised by Tim Gollub)
    • Active Learning for Text Classification (supervised by Christian Kahmann and Christopher Schröder)
    • Incorporating Knowledge Graph Embeddings in Large Language Models (supervised by Ferdinand Schlatt)
    • Normdaten-Disambiguierung und Reconciliation auf Korpusdaten (supervised by Erik Körner and Felix Helfer)
    • Statistical Bootstrap Tests with Redundant Data (supervised by Maik Fröbe)
    • Mining Trigger Warnings from the Web and Social Media (supervised by Matti Wiegmann)
  • Weimar
    • Building an Image Generator for Arguments (supervised by Maximilian Heinrich)
    • From Schemes to Fallacies: A Deep Dive into Argument Classification (supervised by Maximilian Heinrich)
    • Dynamic Generation of Knowledge Graphs for Complex Academic Search Tasks (supervised by Maximilian Heinrich and Tim Gollub)
    • Information Extraction from Scientific PDFs (supervised by Tim Gollub)
    • Adding Contextual Awareness to LLM-based Story Generation (supervised by Tim Gollub)
    • Prompt Framing Effects on Large Language Model Subjectivity Judgements (supervised by Nailia Mirzakhmedova)
    • How Humans Detect Cloned Voices (supervised by Johannes Kiesel and Marcel Gohsen)
    • Automated Conversational Search Evaluation (supervised by Nailia Mirzakhmedova and Johannes Kiesel)
    • Retrieval Augmented Generation for Enhanced Access to Industrial Documentation (supervised by Tim Gollub)
    • Story Orchestration for Multi-Agent Collaboration for Automatic Story Generation (supervised by Marcel Gohsen)
    • Do Large Language Models Extrapolate Personas of Dialog Participants from Context? (supervised by Marcel Gohsen)
    • Developing a Teaching Assistant for Course Materials with Retrieval-Augmented Generation (supervised by Marcel Gohsen)
    • Crafting Multi-Modal Learning Experiences based on Course Materials (supervised by Marcel Gohsen)
    • Health-Related Queries in Large-Scale Query Logs (supervised by Jan Heinrich Merker)
    • Topic Segmentation with Large Language Models (supervised by Johannes Kiesel)
    • Mining Linked Data on Web Scale (supervised by Nikolay Kolyada)
    • Efficient and Effective Neural Translation Language Model for Search (supervised by Harry Scells)
    • Rating the Degree of Search Engine Optimization of Websites (supervised by Janek Bevendorff)

Resources for Students

Vacancies

Research position on Watermarking for Large Language Models at the Bauhaus-Universität Weimar

The Webis Group at the Bauhaus-Universität Weimar (weimar.webis.de) is offering a three-year research position in a joint BMBF project with the Fraunhofer IDMT and Artifact GmbH. Salary is based on the collective agreement for the public sector in Germany, TV-L 13, 100%. The engagement can start immediately, but we are also flexible if the start date of a suitable candidate is later this year. There is the possibility of further employment in our research group.

The offered position deals with innovations and current developments in the field of Text Watermarking and Large Language Models and is very attractive for PhD students or experienced postdocs interested in innovative and fundamental research in the field of Artificial Intelligence, Machine Learning, and Natural Language Processing. The offered position is considered as qualification position, i.e., for non-postdocs we actively support to do a PhD (Dr. rer. nat.).

Prospective candidates should have finished either a master or a PhD in computer science, mathematics, statistics or a related field with excellent or very good grades. Solid knowledge of mathematics and statistics is required for this position - as well as very good programming skills.

We are an experienced research group where team spirit and active collaboration are top priorities. We are looking for open-minded graduates, PhD students, or postdocs who want to develop both as researchers and as a person. The working language of our group is English; fluency in German is not required.

We are interested in increasing the proportion of women in computer science research and particularly welcome applications from suitably qualified women. We do not discriminate on the basis of religion, color, gender, age, or disability and are committed to a family-friendly recruitment policy.

Interested and qualified candidates are invited to submit their application by March 2nd to tim.gollub@uni-weimar.de. The application (preferably as a single PDF file) should contain the following documents: a cover letter describing yourself and your interests, a detailed CV, high school diploma (Abitur), academic transcripts stating courses taken and grades earned, and a list of publications (if any).

Benno Stein
Bauhaus-Universität Weimar
On behalf of the Webis group

Email: webis@listserv.uni-weimar.de
Web: webis.de