Kouta Nakayama

National Institute of Informatics

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Eval Frameworks & Benchmarks (1)RLHF & Preference Learning (1)Constitutional AI & AI Ethics (1)Natural Language Processing (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Momoka Furuhashi (1)Takashi Kodama (1)Saku Sugawara (1)Kyosuke Takami (1)Mutsumi Sasaki (1)

Papers (2)

Sep 28, 2026

2w ago·also NII, Osaka Kyoiku University, UTokyo

How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?

Personalizing LLMs with student profiles improves individual score calibration, yet counterintuitively fails to capture aggregate group-level preferences in educational evaluation.

Momoka Furuhashi, Kouta Nakayama, Takashi Kodama +2

Eval Frameworks & Benchmarks RLHF & Preference Learning

Apr 7, 2026

Mutsumi Sasaki +1Apr 7, 2026·also NII

Exclusive Unlearning

Forget everything bad: a new unlearning method wipes away harmful LLM behaviors by selectively preserving only the knowledge you want.

Mutsumi Sasaki, Kouta Nakayama

Constitutional AI & AI Ethics Natural Language Processing Red-Teaming & Adversarial Robustness

Kouta Nakayama

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)

Search

Kouta Nakayama

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)