Kepu Zhang

Kepu Zhang

M.S. Student At RUC

Kupu Zhang

He is currently a master student at Gaoling School of Artificial Intelligence, Renmin University of China. He is working in IIR lab. His supervisors are AP. Xiao Zhang and Prof. Jun Xu. His major research interests are Search, Recommender Systems, LLM Reasoning and Application, Legal AI, etc.

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
  • Tencent WeChat: Intern
    • March 2025 ~ Now
    • Directions: LLM for Search, AI Search

Skills

Possess experience in large-scale data processing and large-scale LLM training.

  • Programming Language: C, C++, Python
  • Data Processing: Spark, MapReduce, Hadoop
  • Model Training: Megatron, DeepSpeed, Ray, Pytorch, VeRL, TRL, vLLM

Publications

Search and Recommendation

  • Trigger3: Refining Query Correction via Adaptive Model Selector.

    (First author, AAAI 2025, CCF A | LLM for Search)

  • SAQRec: Aligning Recommender Systems to User Satisfaction via Questionnaire Feedback.

    (First author, CIKM 2024, CCF B | Recommendation)

  • Enhancing Explicit Reasoning for Personalized RAG through Contrastive Reward Learning.

    (First author, Under Review | LLM RAG Reasoning)

  • QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors.

    (First author, Under Review | LLM RAG)

  • Logic Rules as Explanations for Legal Case Retrieval.

    (Second author, COLING 2024, CCF B | Retrieval)

LLM Reasoning and Application

  • CitaLaw: Enhancing LLM with Citations in Legal Domain.

    (First author, ACL 2025, CCF A | LLM Citation, RAG)

  • Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning.

    (First author, Under Review | LLM Reasoning)

  • An Explicit Syllogistic Legal Reasoning Framework for Large Language Models.

    (First author, Under Review | LLM RAG Reasoning)

  • Effective In-Context Example Selection through Data Compression.

    (Co-first author, ACL 2024 short findings, CCF A | LLM ICL)

  • Does thermal really always matter for RGB-T salient object detection?

    (Stu-first author, TMM 2023, CCF B | object detection)

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.