Skip to content
conftrace_

language model debiasing

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

pre-trained language model (2) language model (2) debiasing regularization (1) class-wise variance (1) embedding regularization (1) gradient unlearning (1) attribute label (1) factual gender information (1) gradient partitioning (1) implicit social bia (1)

Papers

Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization EMNLP 2024 ADEPT: A DEbiasing PrompT Framework AAAI 2023 Unlearning Bias in Language Models by Partitioning Gradients ACL 2023 Don’t Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information NAACL 2022