Hi! I am a final-year PhD candidate in Computer Science at Columbia University, advised by David Blei. My research is in the intersection of NLP and probabilistic machine learning.

I’m especially interested in:

• developing models that learn interpretable latent concepts from text
• understanding how LLMs encode concepts and implement algorithms through the lens of mechanistic interpretability

During my PhD, I spent two summers interning at Meta in applied AI for ads recommendation. Previously, I completed my undergrad and masters at Penn and worked in Chris Callison-Burch’s lab. I also spent a summer at Columbia Business School working with Andrey Simonov.

email: carozheng at cs dot columbia dot edu
[google scholar] [github] [cv]

Publications

(* = equal contribution)

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 International Conference on Machine Learning, 2024
Mechanistic Interpretability Workshop (Oral)
[paper] [code coming soon!]

Revisiting Topic-Guided Language Models
Carolina Zheng, Keyon Vafa, David Blei
Transactions on Machine Learning Research, 2023
[paper] [code]

An Invariant Learning Characterization of Controlled Text Generation
Carolina Zheng*, Claudia Shi*, Keyon Vafa, Amir Feder, David Blei
Proceedings of ACL, 2023
[paper] [code]

Do Suspense and Surprise Drive Entertainment Demand? Evidence from Twitch.tv
Andrey Simonov, Raluca Ursu, Carolina Zheng
Journal of Marketing Research, 2022
[paper]

Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification
Reno Kriz, João Sedoc, Marianna Apidianaki, Carolina Zheng, Gaurav Kumar, Eleni Miltsakaki, Chris Callison-Burch
Proceedings of NAACL, 2019
[paper]