Zizhong Li

Hello! I am a second-year CS Ph.D. student at the University of California, Davis, advised by Dr.Jiawei Zhang. Prior to UC Davis, I received my B.E. degree in Computer Science from Tongji University in Shanghai, China.

My research interest lies in natural language processing, specifically in nonparametric language modeling, misinformation & information retrieval, and multi-modal generative models.

Recent Papers

[08.2025] [Findings of EACL 2026🌟] Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation arixv blog page

  Zizhong Li, Haopeng Zhang, Jiawei Zhang

  In this paper, we propose Token-level Precise Attack on the RAG (TPARAG), which leverages a lightweight white-box LLM as an attacker to generate and iteratively optimize malicious passages at the token level and is suitable for both white-box and black-box RAG systems.

[10.2024] A Survey of AI-Generated Video Evaluation arxiv

  Xiao Liu∗, Xinhao Xiang∗, Zizhong Li∗¹, Yongheng Wang, Zhuoheng Li, Zhuosheng Liu, Weidi Zhang, Weiqi Ye, Jiawei Zhang

  In this survey, we identify the emerging field of AI-Generated Video Evaluation (AIGVE), highlighting the importance of assessing how well AI-generated videos align with human perception and meet specific instructions.

[06.2024] [IJCNN 2025🌟]Learning by Ranking: Data-Efficient Knowledge Distillation from Black-Box LLMs for Information Retrieval arixv blog page

  Zizhong Li, Haopeng Zhang, Jiawei Zhang

  In this paper, we introduce a data-efficient knowledge distillation training scheme that treats LLMs as black boxes and distills their knowledge via an innovative LLM ranker-retriever pipeline.

[03.2024] [NAACL 2024🌟] Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation arxiv blog page

  Zizhong Li, Haopeng Zhang, Jiawei Zhang

  In this paper, we address this gap by conducting a comprehensive review of attention distillation workflow and identifying key factors influencing the learning quality of retrieval-augmented language models.