De-amplifying Bias from Differential Privacy in Language Model Fine-tuning
CoRR(2024)
摘要
Fairness and privacy are two important values machine learning (ML)
practitioners often seek to operationalize in models. Fairness aims to reduce
model bias for social/demographic sub-groups. Privacy via differential privacy
(DP) mechanisms, on the other hand, limits the impact of any individual's
training data on the resulting model. The trade-offs between privacy and
fairness goals of trustworthy ML pose a challenge to those wishing to address
both. We show that DP amplifies gender, racial, and religious bias when
fine-tuning large language models (LLMs), producing models more biased than
ones fine-tuned without DP. We find the cause of the amplification to be a
disparity in convergence of gradients across sub-groups. Through the case of
binary gender bias, we demonstrate that Counterfactual Data Augmentation (CDA),
a known method for addressing bias, also mitigates bias amplification by DP. As
a consequence, DP and CDA together can be used to fine-tune models while
maintaining both fairness and privacy.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要