About Me

Ph.D. student at SOKENDAI, affiliated with the National Institute of Informatics (NII). Advised by Saku Sugawara.

Research Interests

Scalable oversight, synthetic data generation

News

• [Apr. 2026] Our paper about scalable rubric-augmented reward modeling is accepted to ACL 2026.
• [Sep. 2024] Our paper about LLM-based rationale verification is accepted to EMNLP 2024.

Publications

1. ACL

   C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences

   Akira Kawabata, Saku Sugawara

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026.

   Paper Code To appear


2. EMNLP

   Rationale-Aware Answer Verification by Pairwise Self-Evaluation

   Akira Kawabata, Saku Sugawara

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.

   Paper Code


3. EMNLP

   Evaluating the Rationale Understanding of Critical Reasoning in Logical Reading Comprehension

   Akira Kawabata, Saku Sugawara

   In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

   Paper Code

Work Experience

• Apr. 2023 to Mar. 2026: Research Engineer at The Asahi Shimbun Company

Education

• Apr. 2026 to Present: Ph.D. student, Department of Informatics, The Graduate University for Advanced Studies, SOKENDAI / National Institute of Informatics (NII) (Supervisor: Saku Sugawara)
• Apr. 2021 to Mar. 2023: M.Eng., Nara Institute of Science and Technology (Supervisor: Taro Watanabe)
• Apr. 2016 to Mar. 2021: B.A., Hitotsubashi University

Awards & Scholarships

• Young Researcher’s Encouragement Award, the 29th Annual Meeting of the Association of Natural Language Processing, 2023.
• International News Media Association (INMA) 30 Under 30 Awards, 2025.
• SOKENDAI Special Researcher Program (supported by JST BOOST), 2026 to Present.

Powered by Jekyll and Minimal Light theme.