Zhiyi Yin
6 papers · 2019–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(4)
🏃
Academic Marathon
(6)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(14)
Conferences
ACL (2)
NAACL (2)
EMNLP (1)
IJCAI (1)
Top co-authors
Keywords
harmful content
(2)
adversarial attack
(2)
jailbreak attack
(2)
text generation
(1)
commonsense knowledge
(1)
visual storytelling
(1)
ai safety
(1)
safety alignment
(1)
model alignment
(1)
semantic similarity
(1)
knowledge graph
(1)
generative model
(1)
perturbation robustness
(1)
syntax tree
(1)
llm safety
(1)
llm-generated text detection
(1)
syntactic feature
(1)
syntax tree feature
(1)
large language model
(1)
harmful knowledge
(1)
Papers
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
ACL 2026
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
ACL 2025
Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs
EMNLP 2025
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
NAACL 2025
PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree
NAACL 2025
Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
IJCAI 2019