Search Results for author:
Found 2 papers, 2 papers with code
Linear Adversarial Concept Erasure
Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision.
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
