论文标题
辩护是不够的！ - 关于MLMS及其在下游任务中的社会偏见的有效性
Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks
论文作者
论文摘要
我们研究了掩盖语言模型（MLMS）的任务无关内在和特定于任务的外在社会偏见评估措施之间的关系，并发现这两种类型的评估措施之间仅存在较弱的相关性。此外，我们发现在下游任务进行微调期间，使用不同方法的MLMS DEBIAS进行了重新划分。我们确定两个培训实例中的社会偏见及其分配的标签是内在偏见评估测量值之间差异的原因。总体而言，我们的发现突出了现有的MLM偏见评估措施的局限性，并提出了使用这些措施在下游应用程序中部署MLM的担忧。
We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs), and find that there exists only a weak correlation between these two types of evaluation measures. Moreover, we find that MLMs debiased using different methods still re-learn social biases during fine-tuning on downstream tasks. We identify the social biases in both training instances as well as their assigned labels as reasons for the discrepancy between intrinsic and extrinsic bias evaluation measurements. Overall, our findings highlight the limitations of existing MLM bias evaluation measures and raise concerns on the deployment of MLMs in downstream applications using those measures.
