Scholar
Marius Mosbach
Google Scholar ID: O7RwHEkAAAAJ
Mila - Quebec AI Institute, McGill University
Citations & Impact
Citations
1,698
H-index
14
i10-index
19
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- Awards: Best Paper Award at COLING 2022, Best Theme Paper Award at ACL 2023, Most Interesting Paper Award at BabyLM Challenge 2023
- Papers: Impact of data frequency on LLM unlearning, Analysis of reasoning chains of DeepSeek-R1, etc.
- Workshops: Actionable Interpretability workshop accepted by ICML 2025
Research Experience
- Position: Postdoctoral Researcher
- Work Experience: Formerly a postdoctoral researcher at the Language Science and Technology Department of Saarland University
- Research Projects: Focused on the critical adaptation stage of LLMs to make them more specialized, safe, and aligned with specific requirements
Education
- PhD: Department of Computer Science, Saarland University
- Advisor: Not mentioned
- Time: Not specifically mentioned
Background
- Research Interests: Reliable, controllable, and trustworthy Natural Language Processing (NLP) systems, particularly Large Language Models (LLMs)
- Field: Computer Science
- Introduction: Currently a postdoctoral researcher at Mila - Quebec AI Institute and a postdoctoral fellow at McGill University in Montréal, Canada.
Miscellany
- Personal Interests: CrossFit, playing soccer, occasional baking
