Contact Us
Senior Research Engineer
Kensuke Mitsuzawa, Ph.D. from Eurecom/Sorbonne Université, specializing in interpretable AI, LLM safety, and natural language processing. He completed his postdoctoral research in interpretability and hallucination issues of Large Language Models (LLM) at Université Côte d’Azur in France.
Group Involvement, NEC Laboratories Europe
Reliable GenAI Solutions
Research Interests
- Interpretability and explainability (XAI)
- Natural Language Processing
- Statistical hypothesis testing
Publications
- Kensuke Mitsuzawa, Damien Garreau, MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations, The Second Workshop on Safe AI, the Conference on Uncertainty in Artificial Intelligence (UAI), 2026.
- Kensuke Mitsuzawa, Margherita Grossi, Stefano Bortoli, Motonobu Kanagawa, Variable Selection for Comparing High-dimensional Time-Series Data, arXiv preprint, 2024.
- Kensuke Mitsuzawa, Motonobu Kanagawa, Stefano Bortoli, Margherita Grossi, Paolo Papotti, Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparison, arXiv preprint, 2023.
- Yuta Hayashibe and Kensuke Mitsuzawa, Sentence Boundary Detection on Line Breaks in Japanese. Proceedings of the 6th Workshop on Noisy User-generated Text. 2020. (W-NUT 2020)
- Kensuke Mitsuzawa, Maito Tauchi, Mathieu Domoulin, Masanori Nakashima and Tomoya Mizumoto, FKC Corpus: a Japanese Corpus from New Opinion Survey Service. LREC, 2016.