Zhengxuan Wu
23 papers · 2020–2025 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (39) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(17)
🔬
Deep Specialist
(11)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(101)
Top co-authors
Research topics
Artificial Intelligence
(19)
Core AI
(16)
Machine Learning
(15)
Natural Language Processing
(12)
Deep Learning
(9)
Learning Types · Machine Learning
(8)
Core Methods
(7)
Applications
(5)
Resources & Methods
(5)
Learning Paradigms
(4)
Learning Types · Deep Learning
(4)
Application Areas
(3)
Generation
(3)
Architectures
(2)
Models
(2)
Keywords
language model
(6)
causal abstraction
(6)
causal inference
(5)
neural network
(4)
sentiment analysis
(3)
large language model
(3)
pre-trained language model
(3)
natural language processing
(3)
transfer learning
(3)
representation learning
(3)
concept-based explanation
(2)
distributed representation
(2)
instruction tuning
(2)
model alignment
(2)
attention mechanism
(1)
dataset creation
(1)
few-shot learning
(1)
multi-task learning
(1)
active learning
(1)
text generation
(1)
Papers
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
ICML 2025
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
JMLR 2025
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
EMNLP 2024
Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
CLeaR 2024
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
ICML 2024
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
NAACL 2024
RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
ACL 2024
ReFT: Representation Finetuning for Language Models
NeurIPS 2024
Causal Proxy Models for Concept-based Model Explanations
ICML 2023
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
ACL 2023
Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
NeurIPS 2023
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
EMNLP 2023
Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies
EMNLP 2023
Rigorously Assessing Natural Language Explanations of Neurons
EMNLP 2023
Causal Distillation for Language Models
NAACL 2022
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
NeurIPS 2022
Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models
ACL 2022
Inducing Causal Structure for Interpretable Neural Networks
ICML 2022
ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time
NeurIPS 2022
Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis
AAAI 2021
Dynabench: Rethinking Benchmarking in NLP
NAACL 2021
DynaSent: A Dynamic Benchmark for Sentiment Analysis
ACL 2021
Structured Self-Attention Weights Encode Semantics in Sentiment Analysis
EMNLP 2020