Ailin Tao
2 papers
· 2025–2025
· 2 conferences
· across top CS/AI conferences
Achievements
🌍
Conference Polyglot
(2)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
EMNLP (1)
NAACL (1)
Top co-authors
Keywords
ai safety
(2)
chain-of-thought reasoning
(1)
harmful content
(1)
safety alignment
(1)
adversarial attack
(1)
safety constraint
(1)
refusal behavior
(1)
large language model
(1)
reasoning trajectory
(1)
long chain-of-thought
(1)
path drift
(1)
refusal rate
(1)
metacognitive reflection
(1)
llm vulnerabilities
(1)
model security
(1)
priming attack
(1)