Search Results for author:
Found 3 papers, 0 papers with code
Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models
A few large, homogenous, pre-trained models undergird many machine learning systems — and often, these models contain harmful stereotypes learned from the internet.
Unlocking Fairness: a Trade-off Revisited
The prevailing wisdom is that a model's fairness and its accuracy are in tension with one another.
Scaling Hierarchical Coreference with Homomorphic Compression
In this case, we need the representation to be a homomorphism so that the hash of unions and differences of sets can be computed directly from the hashes of operands.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
