Pengwei Zhan
7 papers · 2021–2024 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
Venues
Top co-authors
Research topics
Machine Learning
(6)
Learning Types · Machine Learning
(6)
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(3)
Natural Language Processing
(3)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Resources & Methods
(2)
Mathematics & Optimization
(1)
Application Areas
(1)
Applications
(1)
Generation
(1)
Models
(1)
Optimization
(1)
Keywords
contrastive learning
(3)
adversarial text attack
(2)
adversarial example
(2)
representation learning
(2)
combinatorial optimization
(2)
query efficiency
(1)
model interpretability
(1)
greedy search
(1)
adversarial attack
(1)
black-box attack
(1)
adversarial defense
(1)
language model
(1)
out-of-distribution detection
(1)
prompt optimization
(1)
search space
(1)
neural language model
(1)
word substitution
(1)
word importance ranking
(1)
text robustness
(1)
black-box adversarial attack
(1)
Papers
Rethinking Word-level Adversarial Attack: The Trade-off between Efficiency, Effectiveness, and Imperceptibility
COLING 2024
Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement
EMNLP 2024
Contrastive Learning with Adversarial Examples for Alleviating Pathology of Language Model
ACL 2023
Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text Attack
ACL 2023
Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training
ACL 2022
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks
COLING 2022
Multimodal Fusion with Co-Attention Networks for Fake News Detection
ACL 2021