[Theory] 3/1 Talks at TTIC: Zhijing Jin, Max Planck Institute and ETH

[Mary Marre]

*When:*        Friday, March 1, 2024 at* 11:00** a**m CT   *


*Where:       *Talk will be given *live, in-person* at

                   TTIC, 6045 S. Kenwood Avenue

                   5th Floor, Room 530


*Virtually:*   *via *Panopto (*livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=d02b7149-1c98-4d17-8431-b122012bc3c4>*
)



*Who: *         Zhijing Jin, Max Planck Institute and ETH


------------------------------
*Title:          *Causal Inference for Robust, Reliable, and Responsible NLP

*Abstract: * 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.

*Bio: *Zhijing Jin (she/her) is a Ph.D. at Max Planck Institute
<https://ei.is.tuebingen.mpg.de/> & ETH <https://ethz.ch/en.html>. Her
research focuses on socially responsible NLP by causal inference.
Specifically, she works on expanding the impact of NLP by promoting NLP for
social good <http://bit.ly/nlp4sg-initiative>, and developing CausalNLP
<https://github.com/zhijing-jin/Causality4NLP_papers> to improve
robustness, fairness, and interpretability of NLP models, as well as causal
analysis of social problems. She has received three Rising Star awards, and
two PhD Fellowships. Her work has been 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 five workshops (including the NLP for
Positive Impact Workshop <https://sites.google.com/view/nlp4positiveimpact> at
EMNLP 2024, and Moral AI Workshop <https://aipsychphil.github.io/> at
NeurIPS 2023), leads the Tutorial on CausalNLP
<https://www.youtube.com/watch?v=4bq1ZYxXbtg&ab_channel=ZhijingJinonAIInsights>
at
EMNLP 2022, and served as the Publications Chair for the 1st
conference on *Causal
Learning and Reasoning <https://www.cclear.cc/2022>* (CLeaR)
<https://www.cclear.cc/2022>. To support diversity, she organizes the ACL
Year-Round Mentorship Program <https://mentorship.aclweb.org/>. More
information can be found on her personal website: zhijing-jin.com


*Host: **David McAllester* <mcallester at ttic.edu>




Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL  60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20240226/743d9f88/attachment.html>