Zeguan Xiao
6 papers · 2021–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (2) π Academic Marathon (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
NAACL (2)
AAAI (1)
ACL (1)
Top co-authors
Keywords
llm safety
(2)
jailbreak attack
(2)
large language model
(2)
multi-task learning
(1)
transfer learning
(1)
prompt engineering
(1)
dependency parsing
(1)
machine unlearning
(1)
safety alignment
(1)
model pruning
(1)
adversarial attack
(1)
uncertainty estimation
(1)
red teaming
(1)
pretrained language model
(1)
graph convolutional network
(1)
adapter module
(1)
llm alignment
(1)
intermediate layer
(1)
syntactic knowledge
(1)
dependency graph
(1)
Papers
Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief
AAAI 2026
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
ACL 2026
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
NAACL 2025
Distract Large Language Models for Automatic Jailbreak Attack
EMNLP 2024
Pruning Adatperfusion with Lottery Ticket Hypothesis
NAACL 2022
BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification
EMNLP 2021