avatar

Haiyan Zhao

Ph.D. Student
New Jersey Institute of Technology
hz54@njit.edu


About Me

I am a second-year graduate student at the Department of Computer Science, New Jersey Institue of Technology(NJIT). Currently, I am working closely with Prof. Mengnan Du on model interpretability. My research interests lie in Explainable AI(XAI), with an emphasis on large language models(LLMs). Before that I obtained my master degree from Huazhong University of Science and Technology(HUST) and my bachelor degree from Wuhan University of Technology(WUT).

Research Interests

XAI, LLM Alignment

News

  • [06/2024] Talk @ IEEE ICHI: Explaining training samples and enhancing trustworthiness with LLM
  • [10/2023] Invited talk @ NJIT FinTech Seminar: Explainability on LLMs
  • [10/2023] Invited talk @ MLLM-AI: Explainability on LLMs
  • [10/2023] Invited talk @ UberAI: Explainability on LLMs

Publications

  1. arXiv
    MemLens: Uncovering Memorization in LLMs with Activation Trajectories
    Zirui He, Haiyan Zhao, Ali Payani and Mengnan Du
    preprint
    PDF

  2. arXiv
    Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
    Haiyan Zhao, Xuansheng Wu, Fan Yang, Bo Shen, Ninghao Liu and Mengnan Du
    preprint
    PDF

  3. arXiv
    A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
    Dong Shu*, Xuansheng Wu*, Haiyan Zhao*, Daking Rai, Ziyu Yao, Ninghao Liu and Mengnan Du
    preprint
    PDF

  4. arXiv
    SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
    Zirui He*, Haiyan Zhao*, Yiran Qiao, Fan Yang, Ali Payani, Jing Ma and Mengnan Du
    preprint
    PDF

  5. arXiv
    Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
    Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Lu Cheng, and Mengnan Du
    EMNLP Findings 2025
    PDF

  6. ICLR
    Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
    Haiyan Zhao, Heng Zhao, Bo Shen, Ali Payani, Fan Yang, Mengnan Du
    ICLR 2025
    PDF Code Project Page

  7. XLLM@ACL 2025
    Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
    Daoyang Li, Haiyan Zhao, Qingcheng Zeng, Mengnan Du
    ACL 2025
    PDF

  8. COLING
    Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
    Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
    COLING 2025
    PDF

  9. arXiv
    Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
    Xuansheng Wu*, Haiyan Zhao*, Yaochen Zhu*, Yucheng Shi*, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu
    preprint
    PDF Code

  10. arXiv
    Towards Uncovering How Large Language Model Works: An Explainability Perspective
    Haiyan Zhao, Fan Yang, Bo Shen, Himabindu Lakkaraju, Mengnan Du
    preprint
    PDF

  11. COLING
    Mitigating Shortcuts in Language Models with Soft Label Encoding
    Zirui He, Huiqi Deng, Haiyan Zhao, Ninghao Liu, Mengnan Du
    COLING 2024
    PDF Code

  12. ACL
    The Impact of Reasoning Step Length on Large Language Models
    Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du
    ACL Findings 2024
    PDF Code

  13. TIST
    Explainability for Large Language Models: A Survey
    Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du
    TIST 2024
    PDF Code

Teaching

Services


Powered by Jekyll and Minimal Light theme.