Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Adam Oberman
Observed name:
Oberman, Adam
Institutions:
Mila - Quebec Artificial Intelligence Institute,
McGill University
Observed institutions:
Mila - Quebec Artificial Intelligence Institute,
McGill University
OpenAlex ID:
A5115997070
Safety from Honesty in a Disinterested AI Predictor
2026
·
Bengio, Yoshua
, Richardson, Oliver
, et al.
·
arXiv (Cornell University)
·
7
PDF
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
2026
·
Merzouk, Mohamed Amine
, Carpov, Dmitri
, et al.
·
arXiv (Cornell University)
·
2
PDF
Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
2025
·
Williams-King, David
, Le, Linh
, et al.
·
arXiv (Cornell University)
·
2
PDF
Efficient Safety Alignment of Language Models via Latent Personality Traits
2026
·
Merzouk, Mohamed Amine
, Smyth, Nolan
, et al.
·
arXiv (Cornell University)
·
1
PDF
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
2026
·
Le, Linh
, Williams-King, David
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
5
Citation count:
12
H-index:
2
I10-index:
Year
Topic
Type
