Kouta Nakayama

Generation of Instruction and Preference Dataset for Improving Japanese Instruction Following in LLMs

AnswerCarefully: Creating a Dataset for LLM Safety in Japanese

Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts

This work constructed a dataset for Japanese claim decomposition and designed detailed guidelines for claim decomposition, ensuring that the extracted claims are in a form useful for fact-checking and that the decomposition rules mitigate annotator variability.

Investigating Learner-Aware Design of LLM-Generated Educational Feedback

Presenting task-relevant information clearly is associated with better immediate revision performance and is favorably evaluated across learner profiles, while descriptive differences in evaluation patterns are observed, particularly for informational novelty and affective framing.

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

It is shown that LLMs still have a limited ability to simulate learner evaluations, and the need to investigate which learner information and adaptation strategies are effective for learner preference simulation is highlighted.