Zhengxuan Wu

Ph.D. Student, Computer Science, Stanford University

Email: wuzhengx [at] cs (dot) stanford (dot) edu

[Google Scholar] [GitHub] [Twitter] [C.V.] [Blog]

Last Update: 10/2024

Hi! I am a third-year Ph.D. student at Stanford University, co-advised by Chris Manning and Chris Potts. Before that, I studied aerospace engineering, and worked in cloud computing.

I am interested in understanding language models and, thus, controlling them.

Selected Publications (*=Equal Contribution)

NeurIPS '24

ReFT: Representation Finetuning for Language Models

Zhengxuan Wu*, Aryaman Arora*, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D. Manning, Christopher Potts

[Blog] [中文介绍] [Github]

NAACL '24

pyvene: A library for understanding and improving PyTorch models via interventions

Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah Goodman, Christopher D. Manning, Christopher Potts

[Github]

NeurIPS '23

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Zhengxuan Wu*, Atticus Geiger*, Christopher Potts, Noah D. Goodman

[Blog] [中文介绍] [Github]

ICML '23

Causal Proxy Models for Concept-Based Explanations

Zhengxuan Wu*, Karel D'Oosterlink*, Atticus Geiger*, Amir Zur, Christopher Potts

[Github]

ICML '22

Inducing Causal Structure for Interpretable Neural Networks

Atticus Geiger*, Zhengxuan Wu*, Hanson Lu*, Josh Rozner, Elisa Kreiss, Thomas Icard, Noah D. Goodman, Christopher Potts

[Github]

NAACL '22

Causal Distillation for Language Models

Zhengxuan Wu*, Atticus Geiger*, Josh Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah D. Goodman

[Github] [OpenReview]

Zhengxuan Wu Your browser does not support the audio element. volume_up

Selected Publications (*=Equal Contribution)

Zhengxuan Wu