Does Differential Privacy Impact Bias in Pretrained NLP Models?

Authors: Md. Khairul Islam1, Andrew Wang1, Tianhao Wang1, Yangfeng Ji1, Judy Fox 1, Jieyu Zhao2

Published: 2024

Publication: ArXiv

Research paper: Does Differential Privacy Impact Bias in Pretrained NLP Models?

Institution: University of Virginia

Research Area: Differential Privacy, Bias Mitigation, LLM, Natural Language Processing (NLP), AI Bias

Discipline: Artificial Intelligence, Natural Language Processing