← Search

Yuzhou Mao

2 accepted papers

2023

Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant Learning

ACL 2023long

Demographic biases and social stereotypes are common in pretrained language models (PLMs), and a burgeoning body of literature focuses on removing the unwanted stereotypical associations from PLMs. However, when fine-tuning these bias-mitigated PLMs in downstream natural language processing (NLP) ap…

Cited by 40SourcePDFScholar
2023

Debiasing Intrinsic Bias and Application Bias Jointly via Invariant Risk Minimization (Student Abstract)

AAAI 2023technical

Demographic biases and social stereotypes are common in pretrained language models (PLMs), while the fine-tuning in downstream applications can also produce new biases or amplify the impact of the original biases. Existing works separate the debiasing from the fine-tuning procedure, which results in…

Cited by 3SourcePDFScholar