Zhijing Jin

Zhijing Jin is an Assistant Professor in the Department of Computer Science at the University of Toronto. Their research interests include natural language processing, large language models, computational social science, machine learning, AI safety, causal inference, and responsible AI. Jin's work focuses on causal methods for NLP, AI safety, and multi-agent LLMs. They are also involved in AI for science and epistemology. Jin's research contributes to AI safety and AI for science, with a focus on causal reasoning with LLMs and multi-agent systems. They are affiliated with the Vector Institute and the Max Planck Institute, and their work has been reported in various media outlets.

Zhijing Jin is a researcher specializing in Natural Language Processing, Causal Inference, Machine Learning, Artificial Intelligence, and LLMs. Their work explores the robustness and fairness of language models, including attacks on text classification and entailment, causal reasoning in language models, and bias analysis in LLMs. Jin also investigates text style transfer, membership inference attacks, and secure data sharing through differentially private language models. Additionally, they focus on generative models for text-to-music, aspect-based sentiment analysis, and the role of explanations in reasoning skills. Their research emphasizes the intersection of NLP and causal inference to improve model reliability and fairness.