📝 Publications

• Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
  arXiv preprint: 2507.00432 • PDF
  Maggie Huan, Yuetai Li, Tuney Zheng, Xiaoyu Xu, Seungone Kim, Minxin Du, Radha Poovendran, Graham Neubig, Xiang Yue

• Unlearning Isn’t Deletion: Investigating Reversibility of Machine Unlearning in LLMs
  arXiv preprint: 2505.16831 • PDF
  Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye, Haibo Hu, Minxin Du

• OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
  EMNLP 2025 (Main Conference): 2505.04416 • PDF
  Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu