Claudia Shi
CS PhD student at Columbia University
Claudia Shi
CS PhD student at Columbia University
Claudia.j.shi AT gmail.com
About
I am broadly interested in machine learning and causal inference. In the past couple of years, I've worked on bringing machine learning insights to causal effect estimation. Recently, I have been thinking about how to ensure large language models produce factual and human-aligned responses. (My hunch: insights from causality can help! )
Aside from my main research, I co-organize the Machine Learning in New York City speaker series and advise AI alignment research projects at FAR AI.
Publications
An Invariant Learning Characterization of Controlled Text Generation
Carolina Zheng*, Claudia Shi*, Keyon Vafa, Amir Feder, David Blei (*equal contribution)
ACL 2023
Evaluating the Moral Beliefs Encoded in LLMs
Nino Scherrer*, Claudia Shi*, Amir Feder, David Blei (*equal contribution)
NeurIPS 2023 (spotlight)
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jeremy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, others
https://arxiv.org/abs/2307.15217
On the Misspecification of Linear Assumptions in Synthetic Control
Achille Nazaret, Claudia Shi, David M. Blei
arXiv:2302.12777, 2023
Causal-structure Driven Augmentations for Text OOD Generalization
Amir Feder, Yoav Wald, Claudia Shi, Suchi Saria, David Blei
NeurIPS, 2023
View all