Search Results for author:
Found 1 papers, 0 papers with code
Conceptor-Aided Debiasing of Large Language Models
We propose two methods of applying conceptors (1) bias subspace projection by post-processing by the conceptor NOT operation; and (2) a new architecture, conceptor-intervened BERT (CI-BERT), which explicitly incorporates the conceptor projection into all layers during training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
