Zhengxuan Wu

发表

Conservation of Procrastination: Do Productivity Interventions Save Time Or Just Redistribute It?

Michael S. Bernstein, Geza Kovacs, Zilin Ma, 2019, CHI.

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

Christopher Potts, Amir Feder, Roi Reichart, 2022, ArXiv.

Causal Distillation for Language Models

Noah D. Goodman, Christopher Potts, Zhengxuan Wu, 2021, NAACL.

Inducing Causal Structure for Interpretable Neural Networks pdf

Christopher Potts, Noah D. Goodman, Thomas Icard, 2021, ArXiv.

Not Now, Ask Later: Users Weaken Their Behavior Change Regimen Over Time, But Expect To Re-Strengthen It Imminently

Michael S. Bernstein, Zhengxuan Wu, Geza Kovacs, 2021, CHI.

ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time

J. Leskovec, Zhengxuan Wu, Tailin Wu, 2022, ArXiv.

Inducing Causal Structure for Interpretable Neural Networks

Noah D. Goodman, Christopher Potts, Zhengxuan Wu, 2021, ICML.

Causal Proxy Models for Concept-Based Model Explanations

Christopher Potts, Zhengxuan Wu, Atticus Geiger, 2022, ICML.

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

Christopher Potts, Amir Feder, Roi Reichart, 2022, NeurIPS.

Upward Flame Spread and Extinction over Wavy Solids

Erik J. Stalcup, J. T’ien, Zhengxuan Wu, 2020 .

Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training

Christopher Potts, Kyle Mahowald, Zhengxuan Wu, 2022, ACL.

ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time

J. Leskovec, Zhengxuan Wu, Tailin Wu, 2022, NeurIPS.

On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification pdf

Desmond C. Ong, Zhengxuan Wu, Zhengxuan Wu, 2021, ArXiv.

Dynabench: Rethinking Benchmarking in NLP pdf

Zhiyi Ma, Christopher Potts, Douwe Kiela, 2021, NAACL.

DynaSent: A Dynamic Benchmark for Sentiment Analysis pdf

Christopher Potts, Douwe Kiela, Atticus Geiger, 2020, ACL.

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Noah D. Goodman, Christopher Potts, Zhengxuan Wu, 2023, ArXiv.

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Christopher D. Manning, Danqi Chen, Christopher Potts, 2023, ArXiv.

Rotating Online Behavior Change Interventions Increases Effectiveness But Also Increases Attrition

Michael S. Bernstein, Geza Kovacs, Zhengxuan Wu, 2018, Proc. ACM Hum. Comput. Interact..

Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models pdf

Christopher Potts, Nelson F. Liu, Zhengxuan Wu, 2021, REPL4NLP.

Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations

Noah D. Goodman, Christopher Potts, Zhengxuan Wu, 2023, CLeaR.

Modeling Emotion in Complex Stories: The Stanford Emotional Narratives Dataset

Desmond C. Ong, Marianne C. Reddan, J. Zaki, 2019, IEEE Transactions on Affective Computing.

Pragmatically Informative Color Generation by Grounding Contextual Modifiers pdf

Desmond C. Ong, Zhengxuan Wu, Zhengxuan Wu, 2020, SCIL.

Oolong: Investigating What Makes Crosslingual Transfer Hard with Controlled Studies

Zhengxuan Wu, Alex Tamkin, Isabel Papadimitriou, 2022, ArXiv.

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Desmond C. Ong, Zhengxuan Wu, Zhengxuan Wu, 2020, AAAI.

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation

Christopher D. Manning, Christopher Potts, Zhengxuan Wu, 2023, Transactions of the Association for Computational Linguistics.

ReaSCAN: Compositional Reasoning in Language Grounding pdf

Christopher Potts, Desmond C. Ong, Elisa Kreiss, 2021, NeurIPS Datasets and Benchmarks.

Rigorously Assessing Natural Language Explanations of Neurons

Christopher Potts, Zhengxuan Wu, Atticus Geiger, 2023, arXiv.org.

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Christopher D. Manning, Danqi Chen, Christopher Potts, 2023, EMNLP.

Structured Self-Attention Weights Encodes Semantics in Sentiment Analysis pdf

Desmond C. Ong, Zhengxuan Wu, Thanh-Son Nguyen, 2020, BLACKBOXNLP.

Mapping the Increasing Use of LLMs in Scientific Papers

Zhengxuan Wu, Haley Lepp, Hancheng Cao, 2024, arXiv.org.

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Zhengxuan Wu, Thomas F. Icard, Atticus Geiger, 2023, 2301.04709.