Meg Tong
4 papers · 2024–2024 · 3 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
logical reasoning
(1)
knowledge editing
(1)
factual knowledge
(1)
reinforcement learning from human feedback
(1)
autoregressive model
(1)
language model
(1)
jailbreaking attack
(1)
adversarial prompt
(1)
contrastive learning
(1)
context window
(1)
reversal curse
(1)
steering vector
(1)
residual stream
(1)
knowledge retrieval
(1)
activation steering
(1)
preference model
(1)
training generalization
(1)
red teaming
(1)