I am a year-1 MPhil student in Computer Science Engineering at Hong Kong University of Science and Technology (HKUST), advised by Prof. Yangqiu Song. Currently, I am working with Dr. Haoran Li on LLM safety and privacy, solving the problem via enhancing legal compliance reasoning. During my undergraduate studies, I had the fortune of working with Prof. Minhao Cheng on backdoor attack on object detection models.

If you are interested in my works or would like to collaborate with me, please feel free to contact me via email (whuak at connect dot ust dot hk).

This webpage is last updated on 2025/05/25.

Research Interests

• LLM Reasoning
• LLM Privacy and Safety
• Legal NLP

Education

• MPhil. in Computer Science at Hong Kong University of Science and Technology, 2025.02 - Now
• BEng. in Computer Science at Hong Kong University of Science and Technology, 2020.09 - 2024.06
• Exchange Semester in Technical University of Munich, 2023.04 - 2023.08

Working Experience

• Research Assistant at Hong Kong University of Science and Technology, 2024.07 - 2025.01

Preprints

• Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning. 2025.
  Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Heli Xu, Tianshu Chu, Peizhao Hu, Yangqiu Song. [paper]

• MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol. 2025.
  Huihao Jing, Haoran Li, Wenbin Hu, Qi Hu, Heli Xu, Tianshu Chu, Peizhao Hu, Yangqiu Song. [paper]

• Node Level Graph Autoencoder: Unified Pretraining for Textual Graph Learning. 2024.
  Wenbin Hu*, Huihao Jing*, Qi Hu*, Haoran Li, Yangqiu Song. [paper]

• Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection. 2023.
  Yize Cheng*, Wenbin Hu*, Minhao Cheng. [paper]

Publication

• PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance. 2025.
  Haoran Li*, Wenbin Hu*, Huihao Jing*, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song
  To appear in ACL 2025 (Main). [paper]

• Mitigating the Alignment Tax of RLHF. 2024.
  Yong Lin*, Hangyu Lin*, Wei Xiong*, Shizhe Diao*, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang.
  EMNLP 2024 (Main). [paper]

(* represents equal contribution.)

Awards and Honors

• Dean’s List (Term GPA > 3.7, top 10 percentile)

Courses

• AI Related Courses: Machine Learning, Deep Learning, Computer Vision, Natural Language Processing, Graph Machine Learning, Reinforcement Learning, Probabilistic Graph Model.
• CS Related Courses: C++, OOP, Computer Architecture, Operation System, Algorithm, Software Engineering, Computer Graphics, Web Search Engine.
• MATH Related Courses: Multivariable Calculus, Linear Algebra, Abstract Algebra, Probability Theory, Convex Optimization, Mathematic Analysis, Ordinary Differential Equation.

Misc.

I have a keen interest in implementing popular methods from scratch. I have developed RLHF (PPO), GPT-2 (training and decoding), etc. [code]