Chong Zhang
Scholar

Chong Zhang

Google Scholar ID: njMEAhIAAAAJ
University of Liverpool
LLM SafetyExplainability for LLMMulti-Agent Systems
Citations & Impact
All-time
Citations
465
 
H-index
11
 
i10-index
12
 
Publications
20
 
Co-authors
12
list available
Resume (English only)
Academic Achievements
  • - Published multiple papers, including but not limited to:
  • - 'AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models'
  • - 'Customized Retrieval-Augmented Generation with LLM for Debiasing Recommendation Unlearning'
  • - 'Goal-guided Generative Prompt Injection Attack on Large Language Models'
Research Experience
  • - Delivered oral presentations at prestigious conferences such as ICDM and ECAI
  • - Actively contributes as a reviewer for renowned journals and conferences including ACL, ACM MM, WWW, IJCV, Pattern Recognition, IJCNN, and ICANN
Education
  • - Xi'an Jiaotong-Liverpool University & University of Liverpool, PhD (Advisor information not provided)
Background
  • - Currently pursuing a PhD at Xi'an Jiaotong-Liverpool University & University of Liverpool
  • - Research interests include Transfer Learning, LLM Safety, Explainability for Large Language Models, and Multi-Agent Systems
Miscellany
  • Interested researchers are welcome to contact me and are sincerely invited to in-depth cooperation.