语言建模中公平性与隐私之间的权衡
Trade-Offs Between Fairness and Privacy in Language Modeling
AI总结：
本文研究文本生成模型中隐私保护与公平性之间的权衡，通过同时引入隐私保护和去偏技术，并借助偏见检测、隐私攻击、语言建模及下游任务实验，揭示沿单一维度优化对另一维度及模型效用的影响。
摘要：
在当代自然语言处理（NLP）模型中保护隐私正变得越来越重要，同时缓解此类模型社会偏见的必要性也在增加。但我们能否同时实现两者？现有研究表明，隐私保护是以加剧分类任务中的偏见为代价的。在本文中，我们探讨了当我们将隐私保护和去偏技术同时纳入文本生成模型训练时，这种权衡在多大程度上确实成立。沿某一维度改进模型会如何影响另一维度以及模型的效用？我们进行了大量实验，涵盖偏见检测、隐私攻击、语言建模以及下游任务性能。
英文摘要：
Protecting privacy in contemporary NLP models is gaining in importance. So does the need to mitigate social biases of such models. But can we have both at the same time? Existing research suggests that privacy preservation comes at the price of worsening biases in classification tasks. In this paper, we explore the extent to which this tradeoff really holds when we incorporate both privacy preservation and de-biasing techniques into training text generation models. How does improving the model along one dimension affect the other dimension as well as the utility of the model? We conduct an extensive set of experiments that include bias detection, privacy attacks, language modeling, and performance on downstream tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
