Education

• 2026.09 - 2029.06, School of Software, Zhejiang University, Hangzhou/Ningbo, China.
• 2022.09 - 2026.06, Computer Science and Engineering College, Northeastern University, Shenyang, China.

Work experience

• 2025.06 - now, Zjunlp Lab, Hangzhou, China.
• 2024.06 - 2025.09, NEUIR Lab, Shenyang, China.

Preprints

(*: equal contribution; †: corresponding author)

• LegalΔ: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
  Xin Dai*, Buqiang Xu*, Zhenghao Liu†, Yukun Yan, Huiyuan Xie, Xiaoyuan Yi, Shuo Wang, Ge Yu
  arXiv preprint arXiv:2508.12281, 2025
  [Paper]

Publications

(*: equal contribution; †: corresponding author)

• LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive Learning
  Buqiang Xu*, Xin Dai*, Zhenghao Liu†, Huiyuan Xie, Xiaoyuan Yi, Shuo Wang, Yukun Yan, Liner Yang, Yu Gu, Ge Yu
  ADMA 2025 (CCF-C) Best Paper Award, Kyoto, Japan, 2025
  [Paper]

🏆 Awards

• 2025.10 Best Paper Award in ADMA 2025, Kyoto, Japan
• 2024.04 Second Prize in the National College Students’ Mathematics Competition Finals