Claudia Shi

Joined

November 2019

Names

Claudia Shi (Preferred)

Emails

****@columbia.edu (Confirmed)

,

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Columbia University (columbia.edu)

2019 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

causal inference

Present

Publications

Extracting Representations in LLMs Robust to Distribution Shifts
Sweta Karlekar, Claudia Shi, Aahlad Manas Puli, Carolina Zheng, Maggie Makar, John Bowlan, Michal Kucer, David Blei
- UCRL@ICLR2026 Poster
- Readers: Everyone
OPENAPPS: SIMULATING ENVIRONMENT VARIATIONS TO MEASURE UI-AGENT RELIABILITY
Karen Ullrich, Jingtong Su, Claudia Shi, Arjun Subramonian, Amir Bar, Ivan Evtimov, Nikolaos Tsilivis, Randall Balestriero, Julia Kempe, Mark Ibrahim
- ICLR 2026 AIWILD
- Readers: Everyone
OPENAPPS: SIMULATING ENVIRONMENT VARIATIONS TO MEASURE UI-AGENT RELIABILITY
Karen Ullrich, Jingtong Su, Claudia Shi, Arjun Subramonian, Amir Bar, Ivan Evtimov, Nikolaos Tsilivis, Randall Balestriero, Julia Kempe, Mark Ibrahim
- Agentic AI in the Wild: From Hallucinations to Reliable Autonomy Poster
- Readers: Everyone
OpenApps: Simulating Environment Variations to Measure UI Agent Reliability
Karen Ullrich, Jingtong Su, Claudia Shi, Arjun Subramonian, Amir Bar, Ivan Evtimov, Nikolaos Tsilivis, Randall Balestriero, Julia Kempe, Mark Ibrahim
- ICLR 2026 Oral
- Readers: Everyone
Hypothesis Testing the Circuit Hypothesis in LLMs
Claudia Shi, Nicolas Beltran-Velez, Achille Nazaret, Carolina Zheng, Adrià Garriga-Alonso, Andrew Jesson, Maggie Makar, David Blei
- ICML 2024 MI Workshop Oral
- Readers: Everyone
Hypothesis Testing the Circuit Hypothesis in LLMs
Claudia Shi, Nicolas Beltran-Velez, Achille Nazaret, Carolina Zheng, Adrià Garriga-Alonso, Andrew Jesson, Maggie Makar, David Blei
- NeurIPS 2024 poster
- Readers: Everyone
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomek Korbak, David Lindner, Pedro Freire, Tony Tong Wang, Samuel Marks, Charbel-Raphael Segerie, Micah Carroll, Andi Peng, Phillip J.K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan et al. (12 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Evaluating the Moral Beliefs Encoded in LLMs
Nino Scherrer, Claudia Shi, Amir Feder, David Blei
- NeurIPS 2023 spotlight
- Readers: Everyone
Data Augmentations for Improved (Large) Language Model Generalization
Amir Feder, Yoav Wald, Claudia Shi, Suchi Saria, David Blei
- NeurIPS 2023 poster
- Readers: Everyone
An Invariant Learning Characterization of Controlled Text Generation
Claudia Shi, Carolina Zheng, Keyon Vafa, Amir Feder, David Blei
- Published: 21 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Workshop DistShift Poster
- Readers: Everyone

View all 12 publications

Co-Authors

View all 58 co-authors