About Me

🎓 About Me

Hi👋, my name is Qi Zhang (张棋 in Chinese), and you can also call me Max.

🏫 I am currently 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 work with Dr. Cornelia Caragea and Dr. Longin Jan Latecki.

📖 My primary research interests are in Natural Language Processing (NLP), Large Language Models (LLMs), and Machine Learning (ML).

🔍 Research Interests

I am broadly interested in building LLM systems that connect language and structured knowledge, and in making LLM agents reliable and safe. Representative directions are highlighted below.

🧩 LLM for Structured Knowledge Extraction

Leveraging LLMs to extract entities, relations, and complex structured knowledge from text (LLM4StructKE).

Named Entity RecognitionRelation ExtractionInformation Extraction

🧠 Structured Knowledge for LLMs

Injecting and utilizing structured knowledge to enhance LLM reasoning, factuality, and adaptability (StructKE4LLM).

Knowledge GraphsRetrieval-Augmented GenerationFactuality

🤖 LLM Agents

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

Tool UseMulti-Agent SystemsReasoning

🛡️ AI Agent Safety

Advancing the safety and reliability of AI agents: tool-use safety, robustness, anomaly detection, and secure multi-step decision making.

Tool-Use SafetyRobustnessAnomaly Detection

🔥 News and Updates

2026.04 🎓 Successfully finished the Ph.D. dissertation defense!!! I am Dr. Zhang now!
2026.04 🎉 Four papers accepted to ACL 2026, see you in San Diego!!!
2026.03 🚀 Started as Applied Scientist at AWS GuardDuty!
2025.09 💼 Started Applied Scientist Intern at AWS. I am fortunate to work with Dr. Qian Cui and Dr. Zhilu Zhang.
2025.05 🌞 Started summer research intern at Intuit AI Research Center. I am fortunate to work with Dr. Xiang Gao and Dr. Yuguang Yao.
2025.04 🎉 One paper has been accepted to ACL 2025!!!
2025.01 🎉 One paper has been accepted to NAACL 2025, see you in Albuquerque, New Mexico!!!

📝 Selected Publications

Underline means equal contribution. For a full list, see my Google Scholar.

Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition

Qi Zhang, Fangping Lan, Cornelia Caragea, Longin Jan Latecki, Eduard Dragut

ACL 2026, Findings

RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning

Xiang Gao, Yuguang Yao, Qi Zhang, Kun Dong, Avirup Baidya, Rui Guo, Hugo Hasson, Kanak Das

ACL 2026, Main

Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications

Fangping Lan, Qi Zhang, Eduard Dragut

ACL 2026, Findings

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

Qi Zhang, Xu Shen, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen

ACL 2026, Findings

DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition

Qi Zhang, Huitong Pan, Zhijia Chen, Longin Jan Latecki, Cornelia Caragea, Eduard Dragut

NAACL 2025, Findings

Taxonomy-Driven Knowledge Graph Construction for Domain-Specific Scientific Applications

Huitong Pan, Qi Zhang, Eduard Dragut, Cornelia Caragea, Longin Jan Latecki

ACL 2025, Findings

Querying Climate Knowledge: Semantic Retrieval for Scientific Discovery

Mustapha Adamu, Qi Zhang, Huitong Pan, Eduard Dragut, Longin Jan Latecki

ACM SIGIR 2025 Workshop MANILA

ClimateIE: A Dataset for Climate Science Information Extraction

Huitong Pan, Mustapha Adamu, Qi Zhang, Eduard Dragut, Longin Jan Latecki