研究成果

Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases

Hui Huang, Xuanxin Wu, Muyun Yang, Yuki Arase

ACL 2026 Workshop on Evaluating Evaluations (EvalEval)

2026年7月

An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment

Xuanxin Wu, Yuki Arase

ACM Transactions on Intelligent Systems and Technology (ACM TIST)

2026年4月

巻・号・ページ: Vol. 17 , No. 4

Edit Policy-Aligned Text Simplification

Xuanxin Wu, Yuki Arase, Masaaki Nagata

AACL-IJCNLP 2026

2026