Alina Klerings
Research Assistant
University of Mannheim
Institute for Enterprise Systems
L 15, 1–6
68161 Mannheim
Institute for Enterprise Systems
L 15, 1–6
68161 Mannheim
E-mail: alina.kleringsuni-mannheim.de
Research Interests
- Safe and Responsible AI
- Interpretability, Evaluation and Robustness of Language Models
- Applied Machine Learning for the Energy Sector, Crisis Response and Humanitarian Aid
Short CV
| Since 2023 | Researcher at Institute for Enterprise Systems and NLP group |
|---|---|
| 2020–2023 | Master of Science in Data Science in University Mannheim |
| 2016–2020 | Bachelor of Arts in Computerlinguistics at Ruprecht-Karls-University Heidelberg |
Publications
- Klerings, A., Brinkmann, J., Stuckenschmidt, H., & Ponzetto, S. P. (2026). Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment. arXiv preprint arXiv:2608.05409
- Klerings, A., Brinkmann, J., Ruffinelli, D., & Ponzetto, S. P. (2025). Steering language models in multi-token generation: A case study on tense and aspect. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 8632-8650).
- Klerings, A., Bartelt, C., & Mueller, A. (2024). Developmentally plausible multimodal language models are highly modular. In The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning (pp. 118–139).