arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.01094cs.CL
收藏

减少预训练模型中内隐性别偏见的对抗性示例生成

Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models

Wenqian Ye, Fei Xu, Yaojia Huang, Cassie Huang, Ji A

摘要:

在过去的几年里,情境化的预训练神经语言模型,如BERT,GPT,在各种NLP任务中表现出显着的进步。为了增强现有预训练模型的鲁棒性,一种方法是对抗性示例生成和评估,以进行数据增强或对抗性学习。与此同时,在实际应用中,嵌入在模型中的性别偏见似乎是一个严重的问题。许多研究都涉及到了词汇层面的性别偏见(如性别刻板印象职业),而很少有研究涉及词汇层面的性别偏见和内隐性别偏见。本文提出了一种自动生成隐性性别偏见样本的方法和一种衡量性别偏见的指标。我们的方法生成的样品将在准确性方面进行评估。该指标将用于指导从预训练模型生成示例。因此,这些示例可以用于对预训练模型进行攻击。最后,我们讨论了我们生成的例子对减少性别偏见的评估功效,为未来的研究。

英文摘要:

Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples generation and evaluation for conducting data augmentation or adversarial learning. In the meanwhile, gender bias embedded in the models seems to be a serious problem in practical applications. Many researches have covered the gender bias produced by word-level information(e.g. gender-stereotypical occupations), while few researchers have investigated the sentence-level cases and implicit cases. In this paper, we proposed a method to automatically generate implicit gender bias samples at sentence-level and a metric to measure gender bias. Samples generated by our method will be evaluated in terms of accuracy. The metric will be used to guide the generation of examples from Pre-trained models. Therefore, those examples could be used to impose attacks on Pre-trained Models. Finally, we discussed the evaluation efficacy of our generated examples on reducing gender bias for future research.

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。

↑