zen
@stanfordnlp
Photo

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: 10/2023

Hi! I am a second-year Ph.D. student at Stanford University, co-advised by Chris Manning and Chris Potts. I received my Master's degree from Symbolic Systems Program at Stanford University. Before that, I received my Bachelor's degree in aerospace engineering, and worked in cloud computing.

I am interested in building interpretable and robust NLP systems.

Selected Publications (*=Equal Contribution)



2023

preprint
Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
Atticus Geiger*, Zhengxuan Wu*, Christopher Potts, Thomas Icard, Noah D. Goodman
EMNLP '23 @BlackBoxNLP
Rigorously Assessing Natural Language Explanations of Neurons
Jing Huang, Atticus Geiger, Karel D'Oosterlinck, Zhengxuan Wu, Christopher Potts
EMNLP '23
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-hop Questions
Zexuan Zhong*, Zhengxuan Wu*, Christopher D. Manning, Christopher Potts, Danqi Chen
[Github]
EMNLP '23
Oolong: Investigating What Makes Crosslingual Transfer Hard with Controlled Studies
Zhengxuan Wu*, Isabel Papadimitriou*, Alex Tamkin*
TACL '23
ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
Zhengxuan Wu, 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
ACL '23 Findings
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
Jing Huang, Zhengxuan Wu, Kyle Mahowald, Christopher Potts
ICML '23
Causal Proxy Models for Concept-Based Explanations
Zhengxuan Wu*, Karel D'Oosterlink*, Atticus Geiger*, Amir Zur, Christopher Potts
[Github]
2022

NeurIPS '22
ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time
Tailin Wu, Megan Tjandrasuwita, Zhengxuan Wu, Xuelin Yang, Kevin Liu, Rok Sosic, Jure Leskovec
NeurIPS '22
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
Eldar David Abraham*, Karel D'Oosterlink*, Amir Feder*, Yair Gat*, Atticus Geiger*, Christopher Potts*, Roi Reichart*, Zhengxuan Wu*
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
ACL '22 @RepL4NLP
Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models
Zhengxuan Wu, Nelson F. Liu, Christopher Potts
[Best Paper Award] [Github]
2021

NeurIPS '21
ReaSCAN: Compositional Reasoning in Language Grounding
Zhengxuan Wu*, Elisa Kreiss*, Desmond C. Ong, Christopher Potts
ACL '21
DynaSent: A Dynamic Benchmark for Sentiment Analysis
Christopher Potts*, Zhengxuan Wu*, Atticus Geiger, Douwe Kiela
NAACL '21
Dynabench: Rethinking Benchmarking in NLP
Douwe Kiela, Max Bartolo, Yixin Nie, Divyansh Kaushik, Atticus Geiger, Zhengxuan Wu, Bertie Vidgen, Grusha Prasad, Amanpreet Singh, Zhiyi Ma, Tristan Thrush, Sebastian Riedel, Zeerak Waseem, Pontus Stenetorp, Robin Jia, Mohit Bansal, Christopher Potts, Adina Williams
AAAI '21
Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis
Zhengxuan Wu, Desmond C. Ong
[Github]
CHI '21
Not Now, Ask Later: Users Weaken Their Behavior Change Regimen Over Time, But Expect To Re-Strengthen It Imminently
Geza Kovacs, Zhengxuan Wu, Michael S. Bernstein
SCiL '21
Pragmatically Informative Color Generation by Grounding Contextual Modifiers
Zhengxuan Wu, Desmond C. Ong
[Github]
Before 2020

arXiv, toolkit
On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification
Zhengxuan Wu, Desmond C. Ong
[Github]
EMNLP '20 @BlackBoxNLP
Structured Self-Attention Weights Encode Semantics in Sentiment Analysis
Zhengxuan Wu, Thanh-Son Nguyen Desmond C. Ong
[Github]
CHI '18
Conservation of Procrastination: Do Productivity Interventions Save Time or Just Redistribute It?
Geza Kovacs, Drew Mylander Gregory, Zilin Ma, Zhengxuan Wu, Zilin Ma, Golrokh Emami, Jacob Ray, Michael S. Bernstein
CSCW '18
Rotating Online Behavior Change Interventions Increases Effectiveness But Also Increases Attrition
Geza Kovacs, Zhengxuan Wu, Michael S. Bernstein