CV

Doctoral Researcher

Technical University of Munich (TUM), Social Computing Group

Research, teaching, and project leadership at the intersection of NLP, multimodal learning, and trustworthy AI. Responsible for the full cycle from project acquisition and design through research execution to publication and student mentorship.

• Led the COLEX research project as PI (Software Campus / BMBF, 2022–2024), managing a team of 5. Delivered a working prototype demonstrated at the Software Campus Summit and handed off to industry partner DATEV.
• Conducted the technical track of the EMF project (2023–2025): collected and analyzed approximately 400k social media posts across platforms, producing a misinformation landscape analysis that informed the BfS public communication strategy and resulted in a recommendation action plan for misinformation handling.
• Contributed to the HUILE project (Siemens collaboration, 2021–2023) on human-in-the-loop techniques for enterprise NLP, delivering an internal prototype handed off to Siemens.
• Designed and taught six courses and lab courses across NLP, explainability, and AI ethics (2020–2025).
• Supervised approximately 30 master’s theses and 6 bachelor’s theses spanning content moderation, legal NLP, misinformation detection, and explainability.

Software Developer

Ablacon Inc.

Full-stack development at a medical AI startup building a mapping system for atrial fibrillation treatment. The company has since been acquired by Boston Scientific.

• Built the web frontend and backend (Django, Flask) for Ablacon’s Electrographic Flow visualization platform as part of a 6-person technical team.
• Prototype I contributed to entered the clinical trial pipeline for pre-clinical validation.

NLP Intern

Siemens Corporate Technology

• NLP and semantic modeling for enterprise applications.

Doctoral Candidate

Technical University of Munich (TUM)

Computer Science

• Topic: Trustworthy NLP — investigating data quality, model robustness, and evaluation design across high-stakes domains.
• Supervisor: Prof. Georg Groh, Social Computing Group.
• Expected graduation: 2026.

M.Sc.

Technical University of Munich (TUM)

Data Engineering and Analytics

• Thesis: Bias Detection in Hate Speech Datasets.

B.Sc.

Technical University of Munich (TUM)

Computational Linguistics and Computer Science

M.A.

Ludwig-Maximilians-Universität München (LMU)

German Literature, Political Science, and Law

• ERASMUS exchange year at Queen Mary University of London (2013–2014).

COLEX: Automatic Analysis and Summarization of German Legal Correspondence

Principal Investigator (Software Campus / BMBF / DATEV, 2022–2024). Developed a graph-based retrieval augmentation system leveraging German legal citation structure for improved context in legal document analysis. Created a multi-perspective summarization corpus for court rulings with distinct summary targets. Built an end-to-end prototype with web frontend integrating all components.

• Funded by BMBF via Software Campus.
• Role: Principal Investigator — responsible for project design, hiring, budget, and research direction.

Misinformation Analysis for EMF and 5G Communication

Technical lead for the computational track (Bundesamt für Strahlenschutz, 2023–2025). Responsible for social media data collection, quantitative analysis of public discourse on electromagnetic fields, and exploratory work on misinformation detection methods.

• Funded by the German Federal Office for Radiation Protection (BfS).
• Role: Technical lead for data collection and quantitative analysis.

HUILE: Human-in-the-Loop Techniques for Enterprise Use Cases

Research on human-model collaboration and feedback-driven learning for enterprise NLP systems (Siemens AG collaboration, 2021–2023).

• Industry collaboration with Siemens AG.

Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs

arXiv preprint

Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation

CySoc Workshop at ICWSM 2026

More Than Debunking Misinformation: A Holistic Communication Model for Public Authorities — The Case of Electromagnetic Fields and 5G in Germany

Research Handbook on Public Communication (Edward Elgar), forthcoming

Retrieving Users’ Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis

IEEE 17th International Conference on Semantic Computing (ICSC 2023)

Best Paper Award.

Comparative Analysis of Cross-Lingual Contextualized Word Embeddings

2nd Workshop on Multi-lingual Representation Learning (MRL) at EMNLP 2022

Long Input Dialogue Summarization with Sketch Supervision for Summarization of Primetime Television Transcripts

Workshop on Automatic Summarization for Creative Writing at COLING 2022

Explaining Neural NLP Models for the Joint Analysis of Open- and Closed-Ended Survey Answers

2nd Workshop on Trustworthy NLP (TrustNLP) at ACL 2022

Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community

Proceedings of the International AAAI Conference on Web and Social Media (ICWSM 2022)

Bias and Comparison Framework for Abusive Language Datasets

AI and Ethics, 2(1), 79–101

Mediale Hasssprache und technologische Entscheidbarkeit: Zur ethischen Bedeutung subjektiv-perzeptiver Datenannotationen in der Hate Speech Detection

Medien–Demokratie–Bildung (Springer), 295–310

Anchor-Based Bilingual Word Embeddings for Low-Resource Languages

Proceedings of ACL-IJCNLP 2021 (Volume 2: Short Papers), 227–232

A Scenario-Based Approach to the Design and Use of Ethical AI Models in Managing a Health Pandemic

Institute for Ethics in Artificial Intelligence, Munich

Evaluating Bilingual Word Embeddings on the Long Tail

Proceedings of NAACL-HLT 2018 (Volume 2: Short Papers), 188–193

Lectures

Technical University of Munich

• Advanced NLP (lecture block on data, bias, and ethics, 2023–2025).
• Natural Language Processing (tutorial sessions, WS 2021).

Lab Courses

Technical University of Munich

• NLP Lab Course (2021–2025): continuous project-based NLP course.
• Ethical AI Lab Course (2022–2025, summer term): tackling ethically challenging problems in ML and AI.
• XAI Lab Course (2020–2023, winter term): explainability methods for machine learning.

Seminars

Technical University of Munich

• Advanced NLP Seminar (2022–2025, winter term): recent developments in NLP.
• Ethics for Nerds Seminar (2021–2024, bachelor level): general ethical issues in computer science.
• Ethics in NLP Seminar (2022–2023, summer term): ethical challenges specific to NLP.

Thesis Supervision

Technical University of Munich

• Supervised approximately 30 master’s theses and 6 bachelor’s theses across NLP, content moderation, legal text processing, explainability, and misinformation detection.

ACL Rolling Review (since 2023), NeurIPS (2026), AISTATS, ICWSM, and various workshops

Peer Review

Association for Computational Linguistics (ACL)

Professional Membership

IEEE 17th International Conference on Semantic Computing (ICSC 2023). For: Retrieving Users’ Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis.