Zhexin Zhang

PhD student, Computer Science, Tsinghua University

Joined

September 2021

Names

Zhexin Zhang (Preferred)

Emails

****@163.com (Confirmed)

****@mails.tsinghua.edu.cn (Confirmed)

Personal Links

Career & Education History

PhD student

Computer Science, Tsinghua University (tsinghua.edu.cn)

2022 – 2027

Undergrad student

Computer Science, Tsinghua University (tsinghua.edu.cn)

2018 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Minlie Huang

2022 – 2027

Expertise

natural language processing

safety

ethics

fairness

alignment

2022 – Present

Publications

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
Zhexin Zhang, Junxiao Yang, Yida Lu, Pei Ke, Shiyao Cui, Chujie Zheng, Hongning Wang, Minlie Huang
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
Zhexin Zhang, Yuhao Sun, Junxiao Yang, Shiyao Cui, yuanchao zhang, Hongning Wang, Minlie Huang
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
“Give a Positive Review Only”: An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers
Qinzhou, Zhexin Zhang, Li Zhi, Limin Sun
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Junxiao Yang, Jinzhe Tu, Haoran Liu, Xiaoce Wang, Chujie Zheng, Zhexin Zhang, Caishun Chen, Tiantian He, Hongning Wang, Yew-Soon Ong, Minlie Huang
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
Zhexin Zhang, Junxiao Yang, Yida Lu, Pei Ke, Shiyao Cui, Chujie Zheng, Hongning Wang, Minlie Huang
- Submitted to ICLR 2026
- Readers: Everyone
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
Zhexin Zhang, Yuhao Sun, Junxiao Yang, Shiyao Cui, yuanchao zhang, Hongning Wang, Minlie Huang
- ICLR 2026 Poster
- Readers: Everyone
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Junxiao Yang, Jinzhe Tu, Haoran Liu, Xiaoce Wang, Chujie Zheng, Zhexin Zhang, Shiyao Cui, Caishun Chen, Tiantian He, Hongning Wang, Yew-Soon Ong, Minlie Huang
- ICLR 2026 Poster
- Readers: Everyone
The Dark Side of Empathy: When Dialogue Systems Face Moral Challenges
Zhexin Zhang, Jiale Cheng, Jiawen Deng, Minlie Huang
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Unveiling the Implicit Toxicity in Large Language Models
Jiaxin Wen, Pei Ke, Hao Sun, Zhexin Zhang, Chengfei Li, Jinfeng Bai, Minlie Huang
- EMNLP 2023 Main
- Readers: Everyone
InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning
Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Minlie Huang
- EMNLP 2023 Findings
- Readers: Everyone

View all 17 publications

Co-Authors

View all 39 co-authors