Bio for Invited Talks

Zhijing Jin (she/her) is an incoming assistant professor at the University of Toronto. Her PhD is at Max Planck Institute & ETH. She works on socially responsible NLP by causal inference. Specifically, her research focuses on causal reasoning with LLMs, causal methods to improve robustness, interpretability, and fairness of LLMs, as well as causal analysis of social problems. She has received 3 Rising Star awards, 2 PhD Fellowships. Her work has published at many NLP and AI venues (e.g., ACL, EMNLP, NAACL, NeurIPS, ICLR, AAAI), and featured in MIT News and ACM TechNews. She co-organizes many workshops (e.g., NLP for Positive Impact Workshop at EMNLP 2024, and Moral AI Workshop at NeurIPS 2023), 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. More information can be found on her personal website: zhijing-jin.com

Talk Abstract

Causal Inference for Robust, Reliable, and Responsible NLP

Despite the remarkable progress in large language models (LLMs), it is well-known that natural language processing (NLP) models tend to fit for spurious correlations, which can lead to unstable behavior under domain shifts or adversarial attacks. In my research, I develop a causal framework for robust and fair NLP, which investigates the alignment of the causality of human decision-making and model decision-making mechanisms. Under this framework, I develop a suite of stress tests for NLP models across various tasks, such as text classification, natural language inference, and math reasoning; and I propose to enhance robustness by aligning model learning direction with the underlying data generating direction. Using this causal inference framework, I also test the validity of causal and logical reasoning in models, with implications for fighting misinformation, and also extend the impact of NLP by applying it to analyze the causality behind social phenomena important for our society, such as causal analysis of policies, and measuring gender bias in our society. Together, I develop a roadmap towards socially responsible NLP by ensuring the reliability of models, and broadcasting its impact to various social applications.

Photo

Here are two photos of mine: (1) a talk photo, and (2) a close-up profile photo. Feel free to select the one that best suits your use case, and don’t hesitate to crop it if necessary.