Skip to content
conftrace_

pre-training bia

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

bias transfer hypothesis (1) fairness in machine learning (1) social bias mitigation (1) bias transfer (1) harmful stereotype (1) dataset quality (1) model fairness (1) social bia (1) pre-trained language model (1)

Papers

Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models ACL 2022