Zesheng Shi
3 papers · 2025–2026 · 1 conference · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(7)
Conferences
ACL (3)
Top co-authors
Keywords
jailbreak attack
(2)
model editing
(1)
harmful content
(1)
safety alignment
(1)
model alignment
(1)
backdoor attack
(1)
synthetic datum
(1)
self-play fine-tuning
(1)
knowledge localization
(1)
neuron pruning
(1)
adaptive weighting
(1)
harmful response
(1)
large language model
(1)
reinforcement learning with verifiable reward
(1)
asymmetric chain backdoor
(1)
knowledge unlearning
(1)
poisoning datum
(1)