Chujie Zheng 郑楚杰

Welcome! I am Chujie Zheng, a final-year Ph.D candidate in CoAI Group at Tsinghua University, advised by Prof. Minlie Huang. I was a visiting scholar in PlusLab at UCLA, hosted by Prof. Nanyun (Violet) Peng. You can find my CV here

I have a broad research interest in building scalable, efficient, and trustworthy AI systems. My research goal is to advance and oversee AI systems with minimal human intervention and ensure they work responsibly and transparently
Recently, I focus on building and overseeing general reasoning models. Projects include QwQ, ProcessBench, Qwen2.5-Math-PRM
Previously, I have conducted extensive research on LLMs for social good, with a main focus on building LLMs for emotional support

News

[03/2025] Release QwQ-32B, our heartfelt creation and the (formal) fruition of our large-scale RL journey. Hope you enjoy it❤️ [blog] [🤗 model] [🤗 demo]
[01/2025] Release Qwen2.5-Math-PRM-7B/72B for mathematical reasoning [paper] [🤗 model]
[12/2024] Release ProcessBench for measuring process error identification in mathematical reasoning [paper] [repo] [🤗 data]
[12/2024] Release Yi-Lightning technical report [paper]
[11/2024] Release QwQ-32B-Preview, an experimental model tailored for reasoning. Hope you enjoy it❤️ [blog] [🤗 model] [🤗 demo]
[10/2024] Release Yi-Lightning, which ranks #6 on Chatbot Arena and #3 in Math Category (as of 10/14/2024). Huge congrats to the team!🍻
[05/2024] Our DRO paper is accpeted at ICML 2024 [paper]
[04/2024] Release our paper on LLM alignment via model extrapolation (ExPO) [paper]
[02/2024] Release a GitHub repository of chat templates for HuggingFace LLMs [repo]
[01/2024] Release our paper on safety prompt optimization (DRO) for safeguarding LLMs [paper]
[01/2024] Our PriDe paper is accpeted for Spotlight presentation (5%) at ICLR 2024 [paper]
[11/2023] Start my visiting research at UCLA, hosted by Nanyun (Violet) Peng
[09/2023] Release our paper on debiasing LLMs (PriDe) in MCQ evaluation [paper]

QwQ-32B: Embracing the Power of Reinforcement Learning
Qwen Team
[blog] [🤗 model] [🤗 demo]
QwQ: Reflect Deeply on the Boundaries of the Unknown
Qwen Team
[blog] [🤗 model] [🤗 demo]
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin
[paper] [repo] [🤗 data]
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin
[paper] [🤗 model]
Yi-Lightning Technical Report
01.AI
[paper]
Weak-to-Strong Extrapolation Expedites Alignment
Chujie Zheng, Ziqi Wang, Heng Ji, Minlie Huang, Nanyun Peng
MHFAIA Workshop @ ICML 2024 (80K+ downloads)
[paper] [repo] [🤗 model]
On Prompt-Driven Safeguarding for Large Language Models
Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, Nanyun Peng
ICML 2024 || SeT LLM Workshop @ ICLR 2024 (Oral: 5%)
[paper] [repo]
Large Language Models Are Not Robust Multiple Choice Selectors
Chujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou, Minlie Huang
ICLR 2024 (Spotlight: 5%)
[paper] [repo]
Chat Templates for 🤗 HuggingFace Large Language Models
Chujie Zheng
GitHub Repository (600+ stars)
[repo]

You can find my full paper list on Google Scholar.

Aug 2020 – present. Ph.D candidate in Computer Science and Technology, Tsinghua University. Advisor: Minlie Huang
Nov 2023 – Jun 2024. Visiting Scholar, UCLA. Host: Nanyun (Violet) Peng
Aug 2016 – Jul 2020. B.Sc. in Foundational Mathematics and Physics, Tsinghua University. Major GPA: 3.98/4.00 (ranking 2/59)

Oct 2024 – Present. Research Intern. Qwen Post-training Team, Alibaba Cloud
- Contributed to the QwQ series reasoning model
- Built the ProcessBench benchmark for process error identification in mathematical reasoning
- Contributed to the Qwen2.5-Math-PRM-7B/72B process reward models for mathematical reasoning
Jul 2024 – Oct 2024. Research Intern. AI Alignment Team, 01.AI
- Contributed to Yi-Lightning, which ranks #6 on Chatbot Arena and #3 in Math Category (as of 10/14/2024)

Area Chair: ACL (24/25), EMNLP (24), NAACL (25), ACL Rolling Review (24)
Reviewer: ICLR (25), NeurIPS (24), ICML (24), COLM (24), ACL (22/23), EMNLP (21/22), NAACL (24), EACL (23), ACL Rolling Review (21/22/23), CogSci (24), AAAI (22/23)

Comprehensive Merit Scholarship, Tsinghua University, 2021 – 2024
Chi-Sun YEH (叶企孙) Scholarship (Top 5/100), Department of Physics, Tsinghua University, 2020
Outstanding Undergraduate, Tsinghua University, 2020
China National Scholarship (Top 2/100), 2019
Comprehensive Merit Scholarship, Tsinghua University, 2018

Jul 2024, AI Tlite Think Tank, WAIC 2024. Towards Efficient LLM Alignment
Jun 2024, AI Time. On Prompt-Driven Safeguarding for Large Language Models (ICML 2024) [video]
Feb 2024, AI Time. Large Language Models Are Not Robust Multiple Choice Selectors (ICLR 2024 Spotlight) [video]
Nov 2022, Shanghai AI Lab. Towards Well-behaved Dialogue Systems
Jul 2021, AI Time. Approaches of Empathy Expression and Emotional Support in Dialogue Systems (ACL 2021) [video]
Nov 2020, Biendata & PaperWeekly. Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation (Findings of EMNLP 2020) [video]
Jul 2020, AI Time. KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation (ACL 2020) [video]