Zhijing Jin

Currently a postdoctoral researcher at the Max Planck Institute for Empirical Inference under Bernhard Schölkopf, Zhijing Jin will soon join the University of Toronto as an Assistant Professor. Her work bridges Natural Language Processing, causality, and ethical AI to address challenges in large language model behavior and societal impact.

Research interests include causal reasoning in language models, moral decision-making in AI agents, multi-agent collaboration, and responsible deployment of NLP technologies. She focuses on understanding how models handle ethical dilemmas, political biases, and cooperative dynamics while improving their robustness and alignment.

Her publications explore collaborative LLM evaluation, ethical reasoning frameworks, and causal modeling for trustworthy AI. Key trends include causality-based NLP, LLM alignment, and socially beneficial language technology. Current projects investigate multi-agent debate systems, political bias detection, and responsible AI practices.