Kaize Ding

About

Kaize Ding is a professor at Northwestern University, leading the Reliable and Efficient Autonomous Learning (REAL) Lab. His work involves advancing autonomous learning systems, and he actively mentors students at various levels, including Ph.D., Master's, and undergraduate students. His lab emphasizes research in artificial intelligence, with a focus on developing reliable and efficient learning algorithms. Professor Ding is committed to fostering scientific research, encouraging students with strong programming and mathematical foundations, and promoting participation in top AI conferences. He is open to motivated students and interns interested in contributing to his research in autonomous learning.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Theoretical computer science
• Data Mining
• Information Retrieval
• Natural Language Processing

Selected publications

• AD-LLM: Benchmarking Large Language Models for Anomaly Detection

  2025-01-01 · 5 citations

  articleOpen access

  Tiankai Yang, Yi Nian, Li Li, Ruiyao Xu, Yuangang Li, Jiaqi Li, Zhuo Xiao, Xiyang Hu, Ryan A. Rossi, Kaize Ding, Xia Hu, Yue Zhao. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

  PublisherOA PDFDOI

• A Survey on Model Extraction Attacks and Defenses for Large Language Models

  2025-08-03 · 4 citations

  articleOpen access

  Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and defenses, categorizing attacks into functionality extraction, training data extraction, and prompt-targeted attacks. We analyze various attack methodologies including API-based knowledge distillation, direct querying, parameter recovery, and prompt stealing tech…

  PublisherOA PDFDOI

• Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models

  2025-02-26 · 3 citations

  article

  The evolution of previous Click-Through Rate (CTR) models has mainly been driven by proposing complex components, whether shallow or deep, that are adept at modeling feature interactions. However, there has been less focus on improving fusion design. Instead, two naive solutions, stacked and parallel fusion, are commonly used. Both solutions rely on pre-determined fusion connections and fixed fusion operations. It has been repetitively observed that changes in fusion design may result in differe…

  PublisherDOI

• Explaining Length Bias in LLM-Based Preference Evaluations

  2025-01-01 · 3 citations

  articleOpen access

  Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

  PublisherOA PDFDOI

• Few-Shot Learning on Graphs

  Frontiers in artificial intelligence and applications · 2025-03-17 · 2 citations

  book-chapter

  Graph representation learning has garnered significant attention due to its outstanding performance across numerous real-world applications, such as social network analysis, bioinformatics, and recommendation systems. However, supervised graph representation learning models often struggle with label sparsity, as data labeling is time-consuming and resource-intensive. To address this, few-shot learning on graphs (FSLG) has been proposed, combining the strengths of graph representation learning an…

  PublisherDOI

Frequent coauthors

• Huan Liu

  79 shared

• Jundong Li

  Sun Yat-sen University Cancer Center

  47 shared

• Jianling Wang

  33 shared

• Dingcheng Li

  Cognitive Research (United States)

  19 shared

• Kai Shu

  17 shared

• James Caverlee

  Texas A&M University

  9 shared

• Hanghang Tong

  9 shared

• Ruocheng Guo

  9 shared

Labs

• Reliable and Efficient Autonomous Learning (REAL) Lab @ NorthwesternPI

  I am fortunate to work with the following talented and motivated students:

Awards & honors

• Amazon Research Awards
• AAAI New Faculty Highlights
• SDM Best Posters Award

Similar researchers at Northwestern University

• Elizabeth Tiptonh-33
• Thomas Severinih-23
• Miklos Z Raczh-21