Zhijing Jin

• Program

  AI Safety Science

• Institution

  University of Toronto

• Location

  USA

Dr. Zhijing Jin (she/her) is an incoming Assistant Professor at the University of Toronto, and currently a postdoc at Max Planck Institute in Germany. Her research focuses on Causal Inference for NLP, AI Safety in Multi-Agent LLMs, and AI for Causal Science. She has received three Rising Star awards, two Best Paper awards at NeurIPS 2024 Workshops, two PhD Fellowships, and a postdoc fellowship. She has authored over 65 papers, many of which appear at top AI conferences (e.g., ACL, EMNLP, NAACL, NeurIPS, ICLR, AAAI), and her work have been featured in CHIP Magazine, WIRED, and MIT News. She co-organizes many workshops (e.g., several NLP for Positive Impact Workshops at ACL and EMNLP, and Causal Representation Learning Workshop at NeurIPS 2024), and leads the Tutorial on Causality for LLMs at NeurIPS 2024, and Tutorial on CausalNLP at EMNLP 2022. To support diversity, she organizes the ACL Year-Round Mentorship.

Dr. Jin will work with Dr. Mrinmaya Sachan on a project which aims to enhance the interpretability and evaluation of large language models (LLMs) by distinguishing between genuine reasoning and mere memorization in their operations.