avatar

Xiaotian Ye

Undergraduate Student
BUPT SCS
yexiaotian[AT]bupt.edu.cn


Publications [Google Scholar][Semantic Scholar]

  • Dagger (†) indicates equal contribution as co-first authors.

    • Research Highlights

    1. S&P 2026
      LLM Unlearning Should Be Form-Independent
      Xiaotian Ye, Mengqi Zhang, Shu Wu
      IEEE Symposium on Security and Privacy (S&P), 2026
      PDF Code Oral Presentation

    2. ICLR 2025 Spotlight
      Uncovering Overfitting in Large Language Model Editing
      Mengqi Zhang†, Xiaotian Ye†, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen
      International Conference on Learning Representations (ICLR), 2025
      PDF Code Spotlight

    3. EMNLP 2024
      Knowledge Graph Enhanced Large Language Model Editing
      Mengqi Zhang†, Xiaotian Ye†, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen
      Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
      PDF Code

    Other Publications & Manuscripts

    1. EMNLP 2025 Findings
      UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets
      Wenyu wang, Mengqi Zhang, Xiaotian Ye, Zhaochun Ren, Zhumin Chen, Pengjie Ren
      Findings of the association for computational linguistics: EMNLP 2025
      PDF

    2. EMNLP 2025 Findings
      KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing
      Mengqi Zhang†, Bowen Fang†, Qiang Liu, Xiaotian Ye, Shu Wu, Pengjie Ren, Zhumin Chen et al.
      Findings of the association for computational linguistics: EMNLP 2025
      PDF

    3. Preprint
      Disentangling Knowledge Representations for Large Language Model Editing
      Mengqi Zhang†, Zisheng Zhou†, Xiaotian Ye, Zhaochun Ren, Zhumin Chen, Pengjie Ren
      Preprint, in submission
      PDF

    4. Preprint
      Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms
      Xiaotian Ye, Mengqi Zhang, Shu Wu
      Blogpost preprint, in submission
      PDF


    Last Update: