About Me
- Mutsumi Sasaki is a second-year master’s student (M2) at the Graduate School of Information Sciences, Tohoku University.
- He belongs to the Tohoku NLP Group and specializes in natural language processing.
Education
- Bachelor of Engineering: 2022.04-2025.03 (Early Graduation)
- School of Engineering, Tohoku University
- Supervisor: Prof. Kentaro Inui & Assoc. Prof. Keisuke Sakaguchi
- Master of Information Science: 2025.04-
- Graduate School of Information Sciences, Tohoku University
- Supervisor: Prof. Kentaro Inui & Assoc. Prof. Keisuke Sakaguchi
International Conference
- Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese Wareki
- Author: Mutsumi Sasaki, Go Kamoda, Ryosuke Takahashi, Kosuke Sato, Kentaro Inui, Keisuke Sakaguchi, Benjamin Heinzerling
- Conference: International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics: IJCNLP-AACL 2025
- Paper: ACL Anthology, ArXiv
Preprint
- Exclusive Unlearning
- Author: Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao, Yohei Oseki, Masaru Isonuma
- Paper: ArXiv
Domestic Conference
- LMは日本の時系列構造をどうエンコードするか
- Author: 佐々木睦史, 鴨田豪, 高橋良允, Benjamin Heinzerling, 坂口慶祐
- Conference: In Proceedings of the Thirty-first Annual Meeting of the Association for Natural Language Processing (NLP 2025)
- Paper: PDF
- 排他的逆学習
- Author: 佐々木睦史, 中山功太, 宮尾祐介, 大関洋平, 磯沼大
- Conference: In Proceedings of the Thirty-second Annual Meeting of the Association for Natural Language Processing (NLP 2026)
- Paper: PDF
- 言語モデルにおける共参照解決を担う注意ヘッドの分析
- Author: 澤田紘希, 佐々木睦史, 坂口慶祐, Benjamin Heinzerling
- Conference: In Proceedings of the Thirty-second Annual Meeting of the Association for Natural Language Processing (NLP 2026)
- Paper: PDF
Domestic Workshop
Award
- 言語処理学会第32回年次大会(NLP2026) 若手奨励賞 (20/487, 4.1%)
- Title: 排他的逆学習
- Author: 佐々木睦史 (東北大/NII), 中山功太 (NII), 宮尾祐介, 大関洋平 (東大/NII), 磯沼大 (NII/東北大/東大)
- Conference: In Proceedings of the Thirty-second Annual Meeting of the Association for Natural Language Processing (NLP 2026)
- Paper: PDF
- 言語処理学会第31回年次大会(NLP2025) スポンサー賞(日本経済新聞社 CDIO室賞)
- Title: LMは日本の時系列構造をどうエンコードするか
- Author: 佐々木睦史, 鴨田豪, 高橋良允 (東北大学), Benjamin Heinzerling, 坂口慶祐 (東北大学/理研)
- Conference: In Proceedings of the Thirty-first Annual Meeting of the Association for Natural Language Processing (NLP 2025)
- Paper: PDF
- JPHACKS2024 イノベーター認定 (7/98=7.1%)
- Title: Eigoイスト
- JPHACKS2024 スポンサー賞(ウルシステムズ株式会社賞)
- Title: Eigoイスト
Experiences
- National Institute of Informatics: Research and Development Center for Large Language Models (NII LLNC)
- LLM-jp Research Assistant: 2025.06-Present
- Supervisor: Kouta Nakayama, Yusuke Miyao, Yohei Oseki, Masaru Isonuma
- JPHACKS2024