He is currently a master student at Gaoling School of Artificial Intelligence, Renmin University of China. He is working in IIR lab. His supervisors is Prof. Jun Xu. His major research interests are about LLM for Search, AI Search etc.

🎯 Interest in LLM for Search, AI Search, Generative Retrieval

📬 Welcome to connect (Email: kepuzhang -AT- ruc.edu.cn)

Education

• 09.2023-present Master’s candidate, Gaoling School of Artificial Intelligence, Renmin University of China.
• 09.2019-06.2023 Bachelor of Computer Science and Technology, Beijing Jiaotong University.

Work Experience

• Kuaishou: Research Intern
  • October 2023 ~ December 2024
  • Research Directions: Search and Recommendation
  • Producing three first-author papers and one patent.
• Tencent WeChat: Algorithm Intern
  • March 2025 ~ Now
  • Directions: LLM for Search, AI Search, Deep Research
  • Leveraging 100~1000 GPUs, RL algorithm to train large-scale relevance models and AI search generative models.

Publications

• Trigger³: Refining Query Correction via Adaptive Model Selector.
  Kepu Zhang, Zhongxiang Sun, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Yang Song, Jun Xu.
  (AAAI’25)
  
• CitaLaw: Enhancing LLM with Citations in Legal Domain.
  Kepu Zhang, Weijie Yu, Sunhao Dai, Jun Xu.
  (ACL’25)
  
• SyLeR: A Framework for Explicit Syllogistic Legal Reasoning in Large Language Models.
  Kepu Zhang, Weijie Yu, Zhongxiang Sun, Jun Xu.
  (CIKM’25)
  
• Enhancing Explicit Reasoning for Personalized RAG through Contrastive Reward Learning.
  Kepu Zhang, Teng Shi, Weijie Yu, Jun Xu.
  (CIKM’25)
  
• Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning.
  Kepu Zhang, Guofu Xie, Weijie Yu, Mingyue Xu, Xu Tang, Yaxin Li, Jun Xu.
  (EMNLP’25)
  
• Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning.
  Kepu Zhang, Haoyue Yang, Xu Tang, Weijie Yu, Jun Xu.
  (EMNLP’25)
  
• QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors.
  Kepu Zhang, Zhongxiang Sun, Weijie Yu, Xiaoxue Zang, Kai Zheng, Yang Song, Han Li, Jun Xu.
  (SIGIR’26)
  
• Empowering open-domain LLMs for legal document correction via legal knowledge integration and decoding constraints.
  Kepu Zhang, Weijie Yu, Zhongxiang Sun, Weicong Qin, Jun Xu, Ji-Rong Wen.
  (IPM’26)
  
• SAQRec: Aligning Recommender Systems to User Satisfaction via Questionnaire Feedback.
  Kepu Zhang, Teng Shi, Sunhao Dai, Xiao Zhang, Yinfeng Li, Jing Lu, Xiaoxue Zang, Yang Song, Jun Xu.
  (CIKM’24)
  
• Effective In-Context Example Selection through Data Compression.
  Zhongxiang Sun*, Kepu Zhang* (Co.-First Author), Haoyu Wang, Xiao Zhang, Jun Xu.
  (ACL’24)
  
• Does thermal really always matter for RGB-T salient object detection?.
  Runmin Cong, Kepu Zhang (Stu.-First Author), Chen Zhang, Feng Zheng, Yao Zhao, Qingming Huang, Sam Kwong.
  (TMM’23) When I was an undergrad.
  

Teaching

1. Teaching Assistant, Introduction to Big Data Analytics in RUC, Fall 2024.
2. Teaching Assistant, Introduction to Artificial Intelligence in New Liberal Arts in RUC, Spring 2025.

Skills

Possess experience in large-scale LLM training.

• LLM Training: Megatron, DeepSpeed, Ray, VeRL, vLLM, SGLang
• Others: C, C++, Python, Pytorch, TRL, Spark, MapReduce, Hadoop