PhD at Max Planck Institute & ETH / Incoming Prof at UToronto (2025-)
Email: zjin@cs.toronto.edu
👩‍🎓Google Scholar / 📁CV / @ZhijingJin (Pronounced like “G-Gin Gin”)

I will be an incoming Assistant Professor at the University of Toronto from 2025, and will spend a year as a postdoc at Max Planck Institute and ETH now. I will also be a CIFAR AI Chair, ELLIS advisor, and faculty member at the Vector Institute.

My research areas are Large Language Models (LLMs), Natural Language Processing (NLP), and Causal Inference. Recently I focus on Causal Reasoning with LLMs, which can be applied to Responsible AI, and AI for Science. I also have a rising interest in Multi-Agent LLMs (see our GovSim), and tool-augmented LLMs (following our work CLadder).

News

• I am in Vancouver for NeurIPS during Dec 8-16, with the following 8 events:
  • 1️⃣ Dec 10 (Tue) 9:30am-12: Our “Causality for LLMs“ Tutorial w/ Sergio Garrido + Panel w/ Yoshua Bengio, Bernhard Schölkopf, Jason Wei, Swaroop Mishra, Giambattista Parascandolo. Our related papers: Corr2Cause (ICLR 2024), CLadder (NeurIPS 2023), CausalQuest (2024), Competition of Mechanisms (ACL 2024), and my GitHub paper list CausalNLP_Papers.
  • 2️⃣ Dec 11 (Wed) 11am-2pm: Our GovSim Poster “Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents”
  • 3️⃣ Dec 13 (Fri) 7:30am: My PhD Thesis defense on Zoom (see calendar invite)
  • 4️⃣ Dec 14 (Sat) 2:15pm: Oral of our Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias at CaLM_Workshop
  • 5️⃣ 3:45pm: Oral of our Trolley Problems paper “Language Model Alignment in Multilingual Trolley Problems” @pluralistic_ai Workshop
  • 6️⃣ 4:30-5:30pm: Causality + LM Workshop Panel: Atticus Geiger, Chelsea Finn, Zhijing Jin, Giambattista Parascandolo, Charlotte Bunne, Maria Antoniak
  • 7️⃣ We will present 4 posters at workshops:
    • Dec 14 (Sat) 10:40-11:40am at “West Meeting Room 116, 117”, 11:30-12 at “East Exhibition Hall C”, 2:30-3pm at “East Exhibition Hall C”
    • Dec 15 (Sun): 11:45-12:30 and also 3-3:45pm at “West Ballroom C”.
  • 8️⃣ Dec 15 (Sun): I co-organize the Causal Representation Learning Workshop, where I will chair the 8:45-9:45am talks by Arthur Gretton and Bernhard Schölkopf
• The best way to find me at NeurIPS is to go to any of my poster sessions, or to the Vector Institute lunch Dec 12 (Thu) 12:30 at the Pan Pacific Hotel, Crystal Pavilion Ballroom. Try to avoid Whova as I have difficulty checking messages there.

---

• I am the Mentorship Chair@EMNLP 2024, Communication Chair for CLeaR 2025, and Senior Area Chairs (SAC)@ACL 2025, and NAACL 2025.
• I always welcome motivated students with evidence of strong skills, open to ETH Master students, remote student collaborators in any career stage, and PhD applications. Please check out my Openings page and fill in the corresponding forms. I do not reply to individual emails which show that they didn’t read the Openings page.

Research Highlights

• 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 Keynote@EMNLP 2023 BlackboxNLP Workshop, Tutorial@EMNLP 2022, and talk slides.
• I also extend the broader impact of Causal NLP to social good applications, with foundational work on 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.

Selected Publications

The following list is outdated. For the latest list of my papers, please see my CV or Google Scholar. For citations, feel free to use this .bib file.

To follow talks on my research, please check out my YouTube.