Xiaoyu Xu's Homepage

About Me

I am a Ph.D. student at The Hong Kong Polytechnic University, co-supervised by Prof. Haibo Hu and Dr. Minxin Du.

Before starting my Ph.D., I received my B.Eng. in Electronics and Communication Engineering from Sun Yat-sen University (SYSU) in 2024.

Research Interests

Security, privacy, and reliability of large language models (LLMs).

Machine Unlearning for Large Language Models
LLM Security and Trustworthiness

Education

2020.09 - 2024.06, Bachelor of Engineering in Electronics and Communication Engineering, Sun Yat-sen University (SYSU)
2024.09 - Present, Ph.D. student, The Hong Kong Polytechnic University

Publications

First Author

Rethinking LLM Unlearning: From Safety Constraints to Functional Utility
Xiaoyu Xu, Minxin Du, Li Bai, Junxu Liu, Huadi Zheng, Peizhao Hu, Qingqing Ye, Haibo Hu (PDF)

My first survey on LLM unlearning, and the first to systematically cover functional forgetting: We organize prior work into two categories based on application focus: safety forgetting, including privacy erasure, copyright removal, and harmful suppression, and functional forgetting, including behavior probing, graceful forgetting, and model regularization. We analyze the first category along three dimensions, covering benchmark, unlearning algorithm, and evaluation; and the second category through three representative functional objectives: CoT faithfulness, learning with forgetting, and model regularizer.
FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning
Xiaoyu Xu, Minxin Du, Kun Fang, Zi Liang, Yaxin Xiao, Zhicong Huang, Cheng Hong, Qingqing Ye, Haibo Hu (arXiv)
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
Xiaoyu Xu, Minxin Du, Zitong Li, Zi Liang, Zhibiao Guo, Shiyu Zhang, Peizhao Hu, Qingqing Ye, Haibo Hu (arXiv)
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye, Huadi Zheng, Peizhao Hu, Minxin Du, Haibo Hu (arXiv)
OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu (EMNLP 2025 Main Conference)

Coauthor

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue (arXiv)