Cite
Notes
Only stored in your browser.
Attribution
Representation Noising: A Defence Mechanism Against Harmful Finetuning
arXiv 2024
Embedding-based classifiers can detect prompt injection attacks
Intrinsic Sliced Wasserstein Distances for Comparing Collections of Probability Distributions on Manifolds and Graphs
arXiv 2020
from 3 papers
Carsten Maple
David Atanasov
Domenic Rosati
Frank Rudzicz
Hassan Sajjad
Jan Wehner
Kai Williams
Łukasz Bartoszcze
Md. Ahsan Ayub
Raif Rustamov