Peng Ding
8 papers · 2017–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (7) π Academic Marathon (8) π Renaissance Researcher (5) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(16)
π§
Keyword Pioneer
β
The Questioner
Conferences
SEMEVAL (2)
ACL (1)
EMNLP (1)
ICCV (1)
ICML (1)
IJCNLP (1)
NAACL (1)
Top co-authors
Keywords
large language model
(3)
attention mechanism
(2)
bidirectional lstm
(2)
jailbreak attack
(2)
text classification
(1)
question answering
(1)
prompt engineering
(1)
model safety
(1)
out-of-distribution generalization
(1)
safety alignment
(1)
adversarial attack
(1)
convolutional neural network
(1)
joint representation
(1)
long short-term memory
(1)
adversarial defense
(1)
loss function
(1)
jailbreaking attack
(1)
word embedding
(1)
defense mechanism
(1)
neural attention
(1)
Papers
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
EMNLP 2025
Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement
ACL 2025
A Wolf in Sheepβs Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
NAACL 2024
Entropy-Reinforced Planning with Large Language Models for Drug Discovery
ICML 2024
Conservative Wasserstein Training for Pose Estimation
ICCV 2019
YNU Deep at SemEval-2018 Task 12: A BiLSTM Model with Neural Attention for Argument Reasoning Comprehension
SEMEVAL 2018
YNU_Deep at SemEval-2018 Task 11: An Ensemble of Attention-based BiLSTM Models for Machine Comprehension
SEMEVAL 2018
YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations
IJCNLP 2017