Mengqi Zhang

Mengqi Zhang

Assistant Professor at Shandong University

About me

Hi! I am Mengqi Zhang (张孟奇), a tenure-track Assistant Professor in the School of Computer Science and Technology, Shandong University, and a member of the Information Retrieval Lab. Prior to this position, I earned my Ph.D. degree from the Institute of Automation, Chinese Academy of Sciences (CASIA) and the University of Chinese Academy of Sciences (UCAS), under the supervision of Prof. Liang Wang, and co-advised by Prof. Shu Wu and Prof. Qiang Liu.

My research primarily focuses on the trustworthiness and controllability of large language models (LLMs), with particular interests in knowledge updating, interpretability, and model safety, including tasks such as knowledge editing, machine unlearning, and retrieval-augmented generation (RAG). Previously, I have also conducted extensive research in temporal knowledge graph reasoning and recommender systems.

招生信息 (Recruitment): I am always looking for self-motivated students to work on LLMs. Feel free to reach out if you are interested in pursuing a Master’s degree, a Ph.D., an undergraduate research assistant position, or exploring potential collaborations. 欢迎对大模型研究感兴趣的同学（保研、考研或本科生科研助理）通过邮件与我联系，也欢迎任何形式的学术探讨与合作！ Email: mengqi.zhang [at] sdu [dot] edu [dot] cn

Preprint

  1. Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse.
    Chi Zhang, Mengqi Zhang #, Xiaotian Ye, Runxi Cheng, Zisheng Zhou, Ying Zhou, Pengjie Ren, Zhumin Chen.
  2. Uncovering Context Reliance in Unstructured Knowledge Editing.
    Zisheng Zhou, Mengqi Zhang, Shiguang Wu, Xiaotian Ye, Chi Zhang, Zhumin Chen, Pengjie Ren.
  3. Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms.
    Xiaotian Ye, Mengqi Zhang, Shu Wu

Selected Publications

( * denotes equal contribution, # denotes corresponding author )

  1. Disentangling Knowledge Representations for Large Language Model Editing.
    ICLR 2026. (CAAI-A)
    Mengqi Zhang *, Zisheng Zhou *, Xiaotian Ye, Qiang Liu, Zhaochun Ren, Zhumin Chen, Pengjie Ren
  2. LLM Unlearning Should Be Form-Independent.
    IEEE S&P 2026. (CCF-A)
    Xiaotian Ye, Mengqi Zhang #, Shu Wu
  3. Uncovering Overfitting in Large Language Model Editing.
    ICLR 2025 Spotlight (Top 5.1%). (CAAI-A)
    Mengqi Zhang *, Xiaotian Ye *, Qiang Liu, Shu Wu, Pengjie Ren, Zhumin Chen
  4. KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing.
    Findings of EMNLP 2025. (CCF-B)
    Mengqi Zhang *, Bowen Fang *, Qiang Liu, Xiaotian Ye, Pengjie Ren, Shu Wu, Zhumin Chen, Liang Wang
  5. UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets.
    Findings of EMNLP 2025. (CCF-B)
    Wenyu Wang, Mengqi Zhang #, Xiaotian Ye, Zhaochun Ren, Pengjie Ren, Zhumin Chen
  6. ExcluIR: Exclusionary Neural Information Retrieval.
    AAAI 2025. (CCF-A)
    Wenhao Zhang, Mengqi Zhang #, Shiguang Wu, Jiahuan Pei, Zhaochun Ren, Maarten de Rijke, Zhumin Chen, Pengjie Ren
  7. Knowledge Graph Enhanced Large Language Model Editing.
    EMNLP 2024. (CCF-B)
    Mengqi Zhang *, Xiaotian Ye *, Qiang Liu, Pengjie Ren, Shu Wu, and Zhumin Chen.
  8. Generative Retrieval as Multi-Vector Dense Retrieval.
    SIGIR 2024. (CCF-A) Honorable Mention (最佳论文提名奖)
    Shiguang Wu, Wenda Wei, Mengqi Zhang, Zhumin Chen, Jun Ma, Zhaochun Ren, Maarten de Rijke, Pengjie Ren.
  9. Learning Long- and Short-term Representations for Temporal Knowledge Graph Reasoning.
    WWW 2023. (CCF-A)
    Mengqi Zhang, Yuwei Xia, Qiang Liu, Shu Wu, and Liang Wang.
  10. Learning Latent Relations for Temporal Knowledge Graph Reasoning.
    ACL 2023. (CCF-A)
    Mengqi Zhang, Yuwei Xia, Qiang Liu, Shu Wu, and Liang Wang.
  11. Dynamic Graph Neural Networks for Sequential Recommendation.
    IEEE Transactions on Knowledge and Data Engineering 2023. (CCF-A)
    Mengqi Zhang, Shu Wu, Xueli Yu, Qiang Liu, and Liang Wang.
  12. Deep Contrastive Multiview Network Embedding.
    CIKM 2022.(CCF-B)
    Mengqi Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, and Liang Wang.
  13. Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation.
    IEEE Transactions on Knowledge and Data Engineering 2020. (CCF-A)
    Mengqi Zhang, Shu Wu, Meng Gao, Xin Jiang, Ke Xu, and Liang Wang.
  14. Dynamic Graph Collaborative Filtering.
    ICDM 2020. Regular Paper (CCF-B)
    Xiaohan Li*, Mengqi Zhang *, Shu Wu, Zheng Liu, Liang Wang, and Philip S Yu.

Experiences

School of Computer Science and Technology, Shandong University
[2023.07 – Present]      Assistant Professor

School of Artificial Intelligence, University of Chinese Academy of Sciences
Institute of Automation, Chinese Academy of Sciences
[2019.09 – 2023.06]      Ph.D in Computer Application Technology
Advisor: Professor Liang Wang

School of Mathematics and Systems Science, Beihang University
[2016.09 – 2019.01]      M.Sc. in Mathematics
Advisor: Professor Xin Jiang

School of Mathematics and Computational Science, Xiangtan University
[2012.09 – 2016.06]      B.Sc. in Mathematics
Advisor: Professor Huayi Wei

Professional Services

ACL Rolling Area Chair

Conference Reviewer

  • NeurIPS, ICLR, ICML, KDD, SIGIR, AAAI, ACL, EMNLP, etc.

Journal Reviewer

  • IEEE TKDE, TOIS, Pattern Recognition, IEEE TBD, Neural Networks, etc.

Honors and Awards

  • 2024 SIGIR Honorable Mention (最佳论文提名奖)
  • 2023 CAS Presidential Scholarship (中国科学院院长奖)
  • 2023 Beijing Outstanding Graduate Student Awards (北京市优秀毕业生)
  • 2023 University of CAS Outstanding Graduate Student Awards (中国科学院大学优秀毕业生)