ZW

Zhengxuan Wu

0000-0001-5581-8908

cs.CLcs.AIcs.LGcs.SIAffective ComputingAffect sensing and analysisCognitive PsychologyCommunitycs.CVcs.DL

On Valency

published · living versions

A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs

with Alexa R. Tartaglini, Thaddäus Wiedemer, Martin Wattenberg, Been Kim +1

1 version

W_ybgbmu8qv1 · current

Preprints & journals

49 papers in the corpus · 2019–2026

The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs

Jiachen Zhao, Zhengxuan Wu, David Bau et al.

0 citations

2610.09384v12026arXiv

EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights

Jiayi Geng, Zhengxuan Wu, Kevin S. Chen et al.

0 citations

2610.00492v12026arXiv

Generalization Dynamics of LM Pre-training

Jiaxin Wen, Zhengxuan Wu, Dawn Song et al.

0 citations

2609.33150v12026arXiv

XYEval: Agents say yes to bad advice

Zhengxuan Wu, Yuxuan Li, Oyvind Tafjord et al.

0 citations

2609.23939v12026arXiv

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

Jiachen Zhao, Zhengxuan Wu, Aryaman Arora et al.

0 citations

2606.06667v32026arXiv

PreFT: Prefill-only finetuning for efficient inference

Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu et al.

0 citations

2605.14217v12026arXiv

ADAG: Automatically Describing Attribution Graphs

Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt et al.

0 citations

2604.07615v12026arXiv

Language Model Circuits Are Sparse in the Neuron Basis

Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt et al.

0 citations

2601.22594v22026arXiv

Quantifying large language model usage in scientific papers.

Liang, Weixin, Zhang, Yaohui, Wu, Zhengxuan et al.

79 citations

407600362025Nature human behaviour. 2025;9(12):2599-2609

LLMs Encode Harmfulness and Refusal Separately

Jiachen Zhao, Jing Huang, Zhengxuan Wu et al.

1 citation

2507.11878v52025arXiv

HyperSteer: Activation Steering at Scale with Hypernetworks

Jiuding Sun, Sidharth Baskaran, Zhengxuan Wu et al.

0 citations

2506.03292v12025arXiv

Improved Representation Steering for Language Models

Zhengxuan Wu, Qinan Yu, Aryaman Arora et al.

0 citations

2505.20809v12025arXiv

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation

Joakim Edin, Casper L. Christensen, R'obert Csord'as et al.

0 citations

2505.17630v42025arXiv

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Zhengxuan Wu, Aryaman Arora, Atticus Geiger et al.

0 citations

2501.17148v32025arXiv

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models

Zhengxuan Wu, Yuhao Zhang, Peng Qi et al.

2 citations

2407.21417v12024arXiv

ReFT: Representation Finetuning for Language Models

Zhengxuan Wu, Aryaman Arora, Zheng Wang et al.

17 citations

2404.03592v32024arXiv

Mapping the Increasing Use of LLMs in Scientific Papers

Weixin Liang, Yaohui Zhang, Zhengxuan Wu et al.

54 citations

2404.01268v12024arXiv

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions

Zhengxuan Wu, Atticus Geiger, Aryaman Arora et al.

2 citations

2403.07809v12024arXiv

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Shiqi Chen, Miao Xiong, Junteng Liu et al.

1 citation

2403.01548v32024arXiv

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations

Jing Huang, Zhengxuan Wu, Christopher Potts et al.

0 citations

2402.17700v22024arXiv

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments

Zhengxuan Wu, Atticus Geiger, Jing Huang et al.

0 citations

2401.12631v12024arXiv

Social microclimates and well-being.

Courtney, Andrea L, Baltiansky, Dean, Fang, Wicia M et al.

10 citations

378242222024Emotion (Washington, D.C.). 2024;24(3):836-846

Rigorously Assessing Natural Language Explanations of Neurons

Jing Huang, Atticus Geiger, Karel D'Oosterlinck et al.

3 citations

2309.10312v12023arXiv

People optimally and flexibly process emotional information across multiple modalities

Desmond C. Ong, Karine Jospe, Marianne Reddan et al.

1 citation

5pr6w_v12023PsyArXiv

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

Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning et al.

55 citations

2305.14795v32023arXiv

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Zhengxuan Wu, Atticus Geiger, Thomas Icard et al.

14 citations

2305.08809v32023arXiv

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

Zhengxuan Wu, Christopher D. Manning, Christopher Potts

4 citations

2303.13716v22023arXiv

Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations

Atticus Geiger, Zhengxuan Wu, Christopher Potts et al.

10 citations

2303.02536v42023arXiv

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Atticus Geiger, Duligur Ibeling, Amir Zur et al.

11 citations

2301.04709v42023arXiv

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

Jing Huang, Zhengxuan Wu, Kyle Mahowald et al.

5 citations

2212.09897v22022arXiv

Causal Proxy Models for Concept-Based Model Explanations

Zhengxuan Wu, Karel D'Oosterlinck, Atticus Geiger et al.

7 citations

2209.14279v12022arXiv

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

Tailin Wu, Megan Tjandrasuwita, Zhengxuan Wu et al.

8 citations

2206.15049v32022arXiv

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

Eldar David Abraham, Karel D'Oosterlinck, Amir Feder et al.

10 citations

2205.14140v22022arXiv

Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies

Zhengxuan Wu, Alex Tamkin, Isabel Papadimitriou

10 citations

2202.12312v22022arXiv

Causal Distillation for Language Models

Zhengxuan Wu, Atticus Geiger, Josh Rozner et al.

7 citations

2112.02505v22021NAACL 2022

Inducing Causal Structure for Interpretable Neural Networks

Atticus Geiger, Zhengxuan Wu, Hanson Lu et al.

15 citations

2112.00826v22021arXiv

ReaSCAN: Compositional Reasoning in Language Grounding

Zhengxuan Wu, Elisa Kreiss, Desmond C. Ong et al.

8 citations

2109.08994v12021NeurIPS 2021 (Dataset and Benchmarks Track)

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

Zhengxuan Wu, Nelson F. Liu, Christopher Potts

6 citations

2104.08410v12021arXiv

Dynabench: Rethinking Benchmarking in NLP

Douwe Kiela, Max Bartolo, Yixin Nie et al.

248 citations

2104.14337v12021arXiv

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

21 citations

2101.11743v12021arXiv

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

Zhengxuan Wu, Desmond C. Ong

14 citations

2101.00196v12021arXiv

DynaSent: A Dynamic Benchmark for Sentiment Analysis

Christopher Potts, Zhengxuan Wu, Atticus Geiger et al.

56 citations

2012.15349v12020arXiv

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Zhengxuan Wu, Desmond C. Ong

97 citations

2010.07523v22020AAAI 2021

Structured Self-Attention Weights Encode Semantics in Sentiment Analysis

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

17 citations

2010.04922v12020BlackBoxNLP Workshop at EMNLP 2020

Pragmatically Informative Color Generation by Grounding Contextual Modifiers

Zhengxuan Wu, Desmond C. Ong

0 citations

2010.04372v12020arXiv

Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset.

Ong, Desmond C, Wu, Zhengxuan, Zhi-Xuan, Tan et al.

77 citations

344845692022IEEE transactions on affective computing. 2021;12(3):579-594

Disentangling Latent Emotions of Word Embeddings on Complex Emotional Narratives

Zhengxuan Wu, Yueyi Jiang

7 citations

1908.07817v12019NLPCC2019

Attending to Emotional Narratives

Zhengxuan Wu, Xiyu Zhang, Tan Zhi-Xuan et al.

19 citations

1907.04197v12019arXiv

Uncovering Political Promotion in China: A Network Analysis of Patronage Relationship in Autocracy

Zhengxuan Wu, Jason Luo, Xiyu Zhang

0 citations

1902.00625v12019arXiv

Career total: 75 works. 49 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.