多偏见：一种面向多语言预训练语言模型的全流程去偏方法
Multiple-Debias: A Full-process Debiasing Method for Multilingual Pre-trained Language Models
AI总结：
本文提出Multiple-Debias方法，通过多语言反事实数据增强和多语言Self-Debias，结合参数高效微调，有效减少多语言预训练模型中性别、种族和宗教偏见。
摘要：
多语言预训练语言模型（MPLMs）已成为自然语言处理的重要工具。然而，它们往往表现出与性别、种族和宗教等敏感属性相关的偏见。在本文中，我们介绍了一种全面的多语言去偏方法，称为Multiple-Debias，以解决多语言中的这些问题。通过整合多语言反事实数据增强和多语言Self-Debias，以及参数高效微调，在四个语言中显著减少了三个敏感属性的偏见。我们还扩展了CrowS-Pairs到德语、西班牙语、中文和日语，验证了我们的全流程多语言去偏方法在性别、种族和宗教偏见方面的有效性。我们的实验表明：(i) 多语言去偏方法在有效减轻偏见方面优于单语言方法；(ii) 融合不同语言的去偏信息显著提高了MPLMs的公平性。
英文摘要：
Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this paper, we introduce a comprehensive multilingual debiasing method named Multiple-Debias to address these issues across multiple languages. By incorporating multilingual counterfactual data augmentation and multilingual Self-Debias across both pre-processing and post-processing stages, alongside parameter-efficient fine-tuning, we significantly reduced biases in MPLMs across three sensitive attributes in four languages. We also extended CrowS-Pairs to German, Spanish, Chinese, and Japanese, validating our full-process multilingual debiasing method for gender, racial, and religious bias. Our experiments show that (i) multilingual debiasing methods surpass monolingual approaches in effectively mitigating biases, and (ii) integrating debiasing information from different languages notably improves the fairness of MPLMs.
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。
