Bairu Hou
11 papers · 2020–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (7) π Academic Marathon (5) π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (16)
π§
Keyword Pioneer
π
Century Club
(11)
Conferences
ICML (3)
IJCNLP (2)
NAACL (2)
AACL (1)
ACL (1)
COLING (1)
ICLR (1)
Top co-authors
Keywords
adversarial robustness
(5)
jailbreak attack
(3)
text classification
(3)
language model
(2)
natural language processing
(2)
semantic smoothing
(2)
textual adversarial attack
(2)
adversarial training
(2)
large language model
(2)
masked language model
(1)
semantic analysis
(1)
language model alignment
(1)
prompt learning
(1)
randomized smoothing
(1)
adversarial defense
(1)
hallucination detection
(1)
black-box model
(1)
input transformation
(1)
semantic transformation
(1)
attack robustness
(1)
Papers
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
AACL 2025
Instruction-Following Pruning for Large Language Models
ICML 2025
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
IJCNLP 2025
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation
NAACL 2025
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
ICML 2024
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
NAACL 2024
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
ICLR 2023
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
ICML 2023
OpenAttack: An Open-source Textual Adversarial Attack Toolkit
IJCNLP 2021
OpenAttack: An Open-source Textual Adversarial Attack Toolkit
ACL 2021
Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet
COLING 2020