Skip to content
conftrace_

gradient unlearning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

gradient partitioning (1) implicit social bia (1) causal mediation analysis (1) language model debiasing (1) large language model (1) annotation bia (1) pre-trained transformer (1) social bia (1) pre-trained language model (1) bias mitigation (1)

Papers

Identifying and Mitigating Annotation Bias in Natural Language Understanding using Causal Mediation Analysis ACL 2024 Unlearning Bias in Language Models by Partitioning Gradients ACL 2023