"I suspect the truth is that we are waiting, all of us, against insurmountable odds, for something extraordinary to happen to us."

— Khaled Hosseini

I’m a Research Associate / PhD student at the Semantic Computing Group in Bielefeld University under the supervision of Prof. Dr. Philipp Cimiano.

I am currently working on the project LLM4KMU - LLMs for Small and Medium-sized Enterprises. LLM4KMU aims to adapt and optimize Large Language Models for their application in SMEs. As part of the project, we are building AutoLLM, an experimentation platform which supports users in finding the right open source LLM, fine-tunes the selected models, conducts extensive post-training and evaluation runs - finally supporting the user in making a more informed decision about the models they use for their application.

In addition to the development of the platform, I am also actively researching into the following topics:

• Hallucination Mitigation – e.g. How can inference-time / training-free decoding strategies help mitigate hallucinations?
• Knowledge Conflicts – e.g. Can LMs reliably over-ride parametric knowledge when presented with conflicting in-context knowledge?

If you find common research interests, I am happy to collaborate! 😊

🔔 Updates

• Sep 23, 2026 — Our paper “Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks” has been accepted to the workshop GREEN-AI 2026 co-located with CIKM 2026.
• Sep 14, 2026 — Our paper “AttentionCD: Reducing Factuality Hallucinations in Large Language Models using Task-specific Head-based Contrastive Decoding” has been accepted to the workshop UncertaiNLP 2026 co-located with EMNLP 2026.
• Sep 7, 2026 — Started as a Research Fellow at SPAR Fall 2026 cohort. Will work on the project A Diagnostic Panel of Ground-Truth Probes for Language Models.