I am an Applied Scientist at AWS Security Analytics and AI Research (SAAR) and a Ph.D. Candidate in the Department of Computer & Information Sciences at Temple University.

I am fortunate to be advised by Dr. Eduard Dragut. I also closely collaborate with Dr. Cornelia Caragea and Dr. Longin Jan Latecki.

My research focuses on Natural Language Processing (NLP), Large Language Models (LLMs), and Applied Machine Learning, with a particular interest in:

• LLM Agents
  Developing LLM-based agent systems with capabilities for tool use, safety assurance, and multi-step reasoning.

• AI Agent Safety
  Advancing the safety and reliability of AI agents, with a focus on tool-use safety, robustness, anomaly detection, and secure multi-step decision-making.

• LLM for Structured Knowledge Extraction (LLM4StructKE)
  Leveraging LLMs to extract entities, relations, and complex structured knowledge from text.

• Structured Knowledge for LLMs (StructKE4LLM)
  Injecting and utilizing structured knowledge to enhance LLM reasoning, factuality, and adaptability.

• Homepage: edzq.github.io
• Google Scholar: Qi Zhang's Publications