Ailin Tao
2 papers · 2025–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🐣
Hot Topic Early Bird
Top co-authors
Research topics
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)