Zhijing Jin
Assistant Professor at the University of Toronto
Email: zjin.admin@cs.toronto.edu Research: Google Scholar | CV
𝕏: @ZhijingJin 🦋: ZhijingJin (Pronounced like “G-Gin Gin”)
I am an incoming Assistant Professor at the University of Toronto, and a Research Scientist at the Max Planck Institute with Bernhard Schoelkopf, based in Europe. I am the founder of EuroSafeAI, a CIFAR AI Chair, faculty member at the Vector Institute, faculty affiliate at the Schwartz Reisman Institute, and an ELLIS advisor.
My research areas are Large Language Models (LLMs), Causal Inference, and Responsible AI. Specifically, my vertical work focuses on Causal Reasoning with LLMs (Causal AI Scientist, CLadder, Corr2Cause, Quriosity, Survey), Multi-Agent LLMs (GovSim, SanctSim, MoralSim [Slides] [Blogpost]), and LLM Democracy Defense (website, slides, video, papers). To support the quality of my vertical work, my horizontal work brings in Mechanistic Interpretability (CompMechs, Mem vs Reasoning), and Adversarial Robustness (CRL Defense, TextFooler, AccidentalVulnerability, RouterAttack). My research contributes to AI Safety and AI for Science. Check out my Acceleration Consortium slides today.
I am the recipient of the ELLIS PhD Award, 3 Rising Star awards, 2 Best Paper Awards at NeurIPS 2024 Workshops, and several PhD fellowships at Coefficient Giving and the Future of Life Institute. In the international academic community, I am a co-chair of the ACL Ethics Committee, co-organizer of the ACL Year-Round Mentorship, and a main supporter of the NLP for Positive Impact Workshop series. My work is reported in CHIP Magazine, WIRED, and MIT News.
Our Jinesis AI Lab
We are funded several millions to conduct frontier research on LLMs, Causality, Multi-Agent Systems, and AI Safety. The Jinesis AI Lab has three teams: a Toronto team at UofT and Vector Institute; a European team operationalized with MPI, ETH, and our non-profit research org EuroSafeAI; and a Global team of international researchers with a joint mission in AI and Social Good.
For students who want to work with me, check the applications below.
Check out the complete list of students and alumni on my CV.
*The Jinesis AI Lab is pronounced as “Genesis” (in memory of Prof. Patrick Winston), as we are entering into a new era of humanity due to the rise of AI.
Research Overview
My technical work focuses on causal inference methods for NLP, specifically to address robustness [1,2,3,4], interpretability [4,5], and causal/logical reasoning [6,7,8,9] of LLMs. See my Tutorial@NeurIPS 2024, Keynote@EMNLP 2023 BlackboxNLP Workshop, and Tutorial@EMNLP 2022.
I also extend the broader impact of Causal NLP to social good applications, with foundational work on the NLP for Social Good (NLP4SG) framework [10,11; MIT News], social policy analysis [12,13], gender bias [14,15], and healthcare [16,17,18]. See my Talk@EMNLP 2022 NLP for Positive Impact Workshop, and 5 related workshops I’ve co-organized.
For community service, I co-organize the ACL Year-Round Mentorship (a network of 650+ mentees and 90+ NLP mentors), and provide research guidance [19] and career suggestions.
“Harness the power of AI to make the world a better place.”
Vision of the Jinesis AI Lab@UToronto
Founded in 2025
Watch & Read
Keep in Contact
Keep posted of our latest research & activities by subscribing to the mailing list.