About Me

I am a Ph.D. candidate at The Hong Kong Polytechnic University, co-supervised by Prof. Haibo Hu and Dr. Minxin Du. My research focuses on the security, privacy, and reliability of large language models (LLMs). 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

  • Machine Unlearning for Large Language Models (LLMs):
    Designing efficient and robust algorithms that enable LLMs to selectively forget specific data while preserving their overall capability. My research explores two key scenarios: (i) Single Unlearning: Removing a specific set of data or knowledge from a pre-trained model in a one-time unlearning request. (ii) Continual Unlearning: Extending unlearning to long sequences of deletion requests, addressing catastrophic forgetting.

  • LLM Security and Trustworthiness:
    Investigating the robustness of LLMs against unlearning attacks like relearning and quantization perturbations to ensure safety and integrity in real-world applications.


News

  • August 2025 — Our paper is accepted to EMNLP 2025 (Main Conference)!
  • June 2025 — Invited to review for ACM Transactions on the Web (TWEB).
  • June 2025 — Invited by EMNLP to serve as a secondary (external) reviewer.
  • May 2025 — My personal homepage officially launched!

Publications

First Author

  • 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)

Educations

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

Interests

  • Fitness enthusiast: Passionate about strength training, cardio, and maintaining a healthy lifestyle.
  • Music lover: Enjoy listening to Mandopop artists such as Jay Chou, G.E.M., JJ Lin, and David Tao.