Contact
Pfaffenwaldring 5 b
70569 Stuttgart
Deutschland
Room: 02.018
Office Hours
On request via email.
Subject
I'm a research assitant at IRIS within the Diversity Aware NLP Intelligent Systems group, a third-year PhD candidate at the IMS, and a member of the chair TCL. I'm advised by Dr. Agnieszka Faleńska.
My research focuses on socially embedded AI systems, spanning responsible/ethical AI and sociotechnical approaches to model design, alignment operationalization and objective trade-offs, sociotechnical evaluation and benchmarking, and the downstream social outcomes of human–AI collaboration.
I’m always happy to chat about these topics and explore shared interests. Please feel free to get in touch.
- Inside Transformers: Advanced Topics in LLM Interpretability, Lecturer, SS26
- Advance Deep Learning in Speech and Language Processing, Co-lecturer, WS23/24
- Spoken Dialogue Systems, Co-lecturer, WS23/24
- Advance Deep Learning in Speech and Language Processing, TA, SS23
I supervise student projects, theses in the below listed areas. If you think your skills and interests are a good fit for these topics, please email me.
Thesis/Project Supervision Topics
- Model (LLM) evaluation, benchmarking, and interpretability
- Sociotechnical alignment
- Pluralistic alignment
- Alignment-objective tradeoffs
- Uncertainty calibration for pluralistic alignment
------
Former and Current Students
Yassir El Attar: (Reserach Project) AI Linguistic Signature: Systematic Features of AI-Generated Text Across Domains and Models (under-review)
Gayane Ghazaryan: (Research Project) Sociotechnical Reward Benchmarking
David Tsoi: (M.Sc. Thesis) Reward Trade-offs and Inference-Time Control in Multi-Objective Direct Preference Optimization
Yassir El Attar: (M.Sc. Thesis) Linguistic Drift in Human–AI Co-Writing: How Textual Features Change Under Assistance
KnitTogether: CL Research Summit for Junior Researchers
Check out 2025 Edition (KnitTogether'25)
Topic: Bias and Social Factors in NLP
Blog Post: Link
→ Coming soon: 2026 Edition