ICLR "output distribution analysis" Papers
2 papers found
A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
Yan Scholten, Stephan Günnemann, Leo Schwinn
ICLR 2025posterarXiv:2410.03523
15
citations
Model Equality Testing: Which Model is this API Serving?
Irena Gao, Percy Liang, Carlos Guestrin
ICLR 2025posterarXiv:2410.20247
16
citations