从隐私保护预训练中刻画刻板偏见
Characterizing Stereotypical Bias from Privacy-preserving Pre-Training
AI总结：
本文研究差分隐私文本私有化对BERT语言模型刻板偏见的影响，发现隐私收紧虽总体降低偏见，但在不同社会领域效果不一致，强调需对私有化后的语言模型进行细致的偏见诊断。
摘要：
差分隐私（DP）可以通过利用嵌入空间中词语的空间排列应用于原始文本。我们研究了此类文本私有化对语言模型（LMs）及其刻板关联倾向的影响。由于先前研究已记录语言熟练度与刻板偏见相关，人们可能假设用于文本私有化的技术（已知会降低语言建模能力）会消除不良偏见。通过测试在包含偏见陈述且施加不同程度隐私的文本上训练的BERT模型，我们的研究表明，虽然当隐私收紧时刻板偏见通常会减弱，但文本私有化并不等同于在所有社会领域都一致地减少偏见。这突显了对经历文本私有化的语言模型进行仔细偏见诊断的必要性。
英文摘要：
Differential Privacy (DP) can be applied to raw text by exploiting the spatial arrangement of words in an embedding space. We investigate the implications of such text privatization on Language Models (LMs) and their tendency towards stereotypical associations. Since previous studies documented that linguistic proficiency correlates with stereotypical bias, one could assume that techniques for text privatization, which are known to degrade language modeling capabilities, would cancel out undesirable biases. By testing BERT models trained on texts containing biased statements primed with varying degrees of privacy, our study reveals that while stereotypical bias generally diminishes when privacy is tightened, text privatization does not uniformly equate to diminishing bias across all social domains. This highlights the need for careful diagnosis of bias in LMs that undergo text privatization.
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。
