The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to numerous debiasing methods targeting word level, there has been relatively less attention on biases present at phrase level, limiting the performance of debiasing in discipline domains. In this paper, we propose an automatic multi-token debiasing pipeline called \textbf{General Phrase Debiaser}, which is capable of mitigating phrase-level biases in masked language models. Specifically, our method consists of a \textit{phrase filter stage} that generates stereotypical phrases from Wikipedia pages as well as a \textit{model debias stage} that can debias models at the multi-token level to tackle bias challenges on phrases. The latter searches for prompts that trigger model's bias, and then uses them for debiasing. State-of-the-art results on standard datasets and metrics show that our approach can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.

翻译：预训练语言模型所揭示的社会偏见和不受欢迎的刻板印象正逐渐成为其应用的阻碍。与大量针对词元层面的去偏方法相比，短语层面偏见的关注相对较少，这限制了去偏在专业领域的表现。本文提出了一种自动多词元去偏流程，称为**通用短语去偏器**，能够有效缓解掩码语言模型中的短语级偏见。具体而言，该方法包含一个**短语过滤阶段**（从维基百科页面生成刻板印象短语）和一个**模型去偏阶段**（在多词元层面进行模型去偏以应对短语偏见挑战）。后者通过搜索触发模型偏见的提示，并利用这些提示进行去偏。在标准数据集和评测指标上的最新结果表明，该方法能够显著降低不同参数量模型在职业及多学科领域中的性别偏见。