Welcome! 👋 I am a Postdoctoral Researcher at the Technische Universität Berlin (TU Berlin) under the supervision of Sebastian Möller (Quality and Usability Lab) and the Berlin Institute for the Foundations of Learning and Data (BIFOLD) supervised by Alexander Meyer (DHZC), affiliated with the German Research Center for Artificial Intelligence (DFKI) as a guest researcher.
Research interests 👀
Advancing the interpretability of language models with the goal of increasing trust in and simplifying access to explanations!
I am open to collaborations on rationale generation, text simplification and summarization, concept explanations, biomedical and clinical NLP, and evaluation measures for model-generated text.
News 🤩
| Date | Topic | Item |
|---|---|---|
| Accept | Extremely excited about the NeurIPS 2025 acceptance of the PRISM paper led by Laura Kopf! | |
| Accept | My survey with Laura Kopf on concept descriptions for interpreting language models will appear at the BlackboxNLP workshop, co-located with EMNLP 2025 in Suzhou! | |
| Accept | Our paper on explanation dialogues and measurement of teaching acts led by Aliki has been accepted by the CODI-CRAC workshop at EMNLP 2025! | |
| Talks | Excited to give a talk on human-centric explainable NLP at the AI-based Methods for the Humanities event on September 23! I'll also participate in the "LLMs for Health" NII Shonan Meeting 🇯🇵 in October. | |
| Accept | Our paper on evaluating LLM-generated counterfactuals led by Qianli has been accepted at INLG 2025 in 🇻🇳 Hanoi! | |
| Accept | Our multilingual conversational XAI datasets paper led by Qianli has been accepted for Findings of EMNLP 2025! See you in 🇨🇳 Suzhou! | |
| Service | I'm co-organizing the inaugural YNLG Workshop for Young Researchers in Natural Language Generation! Hope to see you in 🇻🇳 Hanoi! | |
| Award | Our TableEval paper has won the Best Runner-up Paper Award at the Table Representation Learning Workshop! 🥳 | |
| Pre-print | Demo paper and first publication from my IlluminateCardio project on translating free-form clinical notes to structured FHIR resources available on arXiv. This is a collaboration with Uni Augsburg and Charité. | |
| Pre-print | Paper on feature description methods and polysemanticity out on arXiv | |
| Accept | FEVER Shared Task submission accepted for ACL 2025. | |
| Accept | The study on readability of free-text rationales by Yi-Sheng was accepted at the GEM^2 Workshop at ACL 2025. 🧐 | |
| Accept | Our table understanding study led by Ekaterina has been accepted at the Table Representation Learning Workshop of ACL 2025. 📊 | |
| Pre-print | Three papers led by Qianli in submission: One on quantization effects on explainability and interpretability (in collaboration with LMU Munich) 🗜, one on the evaluation of LLM-generated counterfactuals (in collaboration with Uni Marburg) 🪢, and one on multilingual datasets for conversational XAI. 🧭 | |
| Accept | FitCF has been accepted to ACL 2025 Findings! See you in Vienna! 🎡 | |
| Accept | Paper with TU Munich on gender bias in explainability accepted at FAccT 2025. 🦉 | |
| Graduation | Successfully defended my PhD thesis at TU Berlin! 🎓 Thanks to my mentor Sebastian Möller and professors Sina Zarrieß (Uni Bielefeld), Christin Seifert (Uni Marburg) and Matthias Boehm for being part of the committee and awarding the graduation certificate with a "magna cum laude". | |
| Service | First time serving as an editor: Together with Britta Schulte, I published the proceedings of the ISCA-ITG Workshop on Diversity in Large Speech and Language Models. | |
| Supervision | Honored to be (co-)supervising four incredibly talented PhD students at TU Berlin from now on: Arthur Hilbert, Qianli Wang, Luis Felipe Villa-Arenas, and Steffen Castle. | |
| Pre-print | First-author paper on explanation strategies and response generation in conversational XAI in submission. | |
| Talk | I gave an invited talk at the University of Groningen about human-centric explainable NLP. 🇳🇱 | |
| Pre-print | Co-authored paper in submission: FitCF: A Framework for Automatic Feature Importance-based Counterfactual Example Generation. | |
| Recap | I published my 2024 Recap showcasing my favorite papers from this year's major conferences. | |
| Position | I am joining TU Berlin and BIFOLD in January 2025. My project IlluminateCardio will focus on the interpretability of large language models, human-AI alignment, and applications to cardiovascular medicine in collaboration with Prof. Alexander Meyer (Charité). 🏛️🏥 | |
| Accept | Cross-Refine accepted for COLING 2025. |
Education 👨🎓
2021-2025 – Computer Science, PhD, Technische Universität Berlin. Supervised by Sebastian Möller: “Approaches for Generating and Evaluating Natural Language Explanations of Language Models”. (doi)
2016-2020 – Cognitive Systems: Language, Learning and Reasoning, MSc, University of Potsdam. Supervised by Manfred Stede: “Utilizing machine translation for bootstrapping abstractive text summarization”.
2013-2016 – Computational Linguistics, BA, Heidelberg University. Supervised by Katja Markert: “An in-depth investigation on timeline summarization evaluation”.
Jobs 👨💼
2025-2027: Postdoctoral Researcher @ TU Berlin & BIFOLD. Projects: IlluminateCardio (“Interpretable Large Language Models for the Cardiovascular Medicine”), VERANDA (“Trustworthy Anonymization of Sensitive Patient Records for Remote Consultation”).
2020-2024: Researcher/Software Engineer @ German Research Institute for Artificial Intelligence (DFKI), Berlin, Speech and Language Technology group. Projects: 2021-2024 – XAINES - Explaining AI with Narratives project, supervised by Sebastian Möller 2020-2021 – European Language Grid project, supervised by Georg Rehm.
2014: Student assistant at the Institute for Computational Linguistics @ Heidelberg University
Leisure activities and other interests 🎵
Hosting two web radio shows where I mix ambient (Neptunian @ FRISKY Radio, since 2014) and atmospheric electronic music (Idolatry @ Proton Radio, since 2015). I’ve been producing mixes for Mixcloud since 2011. All of these are available on helioscope.net.
Cycling and hiking
Nature photography
Board games
Cinema