Liu Yan
6 papers · 2024–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🐝
Cross-Pollinator
(12)
🌉
Interdisciplinary Bridge
Conferences
EMNLP (3)
ACL (2)
ICLR (1)
Top co-authors
Research topics
Keywords
large language model
(3)
data augmentation
(1)
prompt engineering
(1)
instruction following
(1)
intent detection
(1)
harmful content
(1)
safety alignment
(1)
hidden state
(1)
synthetic datum
(1)
jailbreak attack
(1)
linear probing
(1)
cognitive bia
(1)
training datum
(1)
token analysis
(1)
model internal
(1)
chinese language
(1)
prompt bia
(1)
probing classifier
(1)
linear probe
(1)
prompt leakage
(1)
Papers
Revisiting the Reliability of Language Models in Instruction-Following
ACL 2026
Understanding the Dark Side of LLMs’ Intrinsic Self-Correction
ACL 2025
“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents
EMNLP 2025
Speculating LLMs’ Chinese Training Data Pollution from Their Tokens
EMNLP 2025
A Benchmark for Semantic Sensitive Information in LLMs Outputs
ICLR 2025
Course-Correction: Safety Alignment Using Synthetic Preferences
EMNLP 2024