Biography
Ryosuke Takahashi is a Ph.D. student in the Graduate School of Information Sciences at Tohoku University and a member of the Tohoku NLP Group. He is concurrently enrolled at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) through the Dual Doctoral Degree Program. He is broadly interested in understanding what language models know, how they come to know it, and how that knowledge can be traced, modified, or removed through the lens of mechanistic interpretability.
Research Interests
• Mechanistic Interpretability of LMs
• Knowledge Acquisition, Editing, and Deletion in LMs
• Training Dynamics of LMs
News / Recent Activity
2025-11
Presented a first-author paper at the Eighth Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP 2025), co-located with EMNLP 2025 in Suzhou, China.
Page 1 of 2
