About Me

Hello, I’m Zhi Cheng, currently an LLM Algorithm Engineer at Z.ai (Zhipu AI).

My recent work includes integrating strong reasoning with iterative retrieval-augmented generation (RAG), performing supervised fine-tuning (SFT) on large language model (LLM) for downstream tasks, as well as neuro-symbolic reasoning with LLM for knowledge-based question answering (KBQA).

I earned my Master’s Degree in Computer Science and Technology from Tsinghua University, as a member of the KEG Lab under the supervision of Prof. Juanzi Li.

Prior to embarking on my master’s journey, I had the privilege of gaining valuable work experience at startup, particularly in the development of face anti-spoofing and voice cloning projects.

I earned my Bachelor’s Degree in Automation from Shanghai Jiao Tong University where I conducted research in various areas, including Semi-Supervised Learning and Graph Neural Networks. My enthusiasm for learning and self-improvement drives me forward.

Publications

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
Zhicheng Lee, Shulin Cao, Jinxin Liu, Jiajie Zhang, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li.
ArXiv, 2025

DiaKoP: Dialogue-based Knowledge-oriented Programming for Neural-symbolic Knowledge Base Question Answering
Zhicheng Lee*, Zhidian Huang*, Zijun Yao, Jinxin Liu, Amy Xin, Lei Hou, Juanzi Li.
Conference on Information and Knowledge Management (CIKM demo track), 2024

Deep Semi-Supervised Learning via Dynamic Anchor Graph Embedding Learning
Zihao Wang, Enmei Tu, Zhicheng Lee
International Joint Conference on Neural Networks (IJCNN), 2021