从测量到缓解：探索去偏方法向马耳他语语言模型中性别偏见的可迁移性
From Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models
AI总结：
本文测量马耳他语BERTu和mBERTu模型中的性别偏见，并将英语去偏方法适配到马耳他语进行迁移性研究，揭示现有方法在形态丰富低资源语言上的局限，并创建评估数据集以推动更具包容性的多语言NLP发展。
摘要：
大型语言模型（LLMs）的进步已经改变了自然语言处理（NLP），使得在几乎没有任务特定训练的情况下能够在多种任务上取得良好表现。然而，LLMs仍然容易受到社会偏见的影响，特别是反映训练数据中有害刻板印象的偏见，这可能对边缘化群体造成不成比例的影响。我们测量了马耳他语语言模型中的性别偏见，认为这种偏见是有害的，因为它强化了社会刻板印象，并且未能考虑性别多样性，这在具有语法性别且资源匮乏的语言中尤其成问题。尽管针对以英语为中心的模型的偏见评估和缓解工作已经取得进展，但对资源匮乏且形态丰富的语言的研究仍然有限。本研究探讨了去偏方法向马耳他语语言模型的可迁移性，重点关注BERTu和mBERTu，它们分别是基于BERT的单语和多语模型。来自英语的偏见测量和缓解技术被适配到马耳他语中，使用了CrowS-Pairs和SEAT等基准，以及反事实数据增强（Counterfactual Data Augmentation）、Dropout正则化、Auto-Debias和GuiDebias等去偏方法。我们还通过创建评估数据集为未来马耳他语性别偏见研究做出贡献。我们的发现突显了将现有偏见缓解方法应用于语言结构复杂语言时所面临的挑战，强调了在多语言NLP开发中需要更具包容性的方法。
英文摘要：
The advancement of Large Language Models (LLMs) has transformed Natural Language Processing (NLP), enabling performance across diverse tasks with little task-specific training. However, LLMs remain susceptible to social biases, particularly reflecting harmful stereotypes from training data, which can disproportionately affect marginalised communities. We measure gender bias in Maltese LMs, arguing that such bias is harmful as it reinforces societal stereotypes and fails to account for gender diversity, which is especially problematic in gendered, low-resource languages. While bias evaluation and mitigation efforts have progressed for English-centric models, research on low-resourced and morphologically rich languages remains limited. This research investigates the transferability of debiasing methods to Maltese language models, focusing on BERTu and mBERTu, BERT-based monolingual and multilingual models respectively. Bias measurement and mitigation techniques from English are adapted to Maltese, using benchmarks such as CrowS-Pairs and SEAT, alongside debiasing methods Counterfactual Data Augmentation, Dropout Regularization, Auto-Debias, and GuiDebias. We also contribute to future work in the study of gender bias in Maltese by creating evaluation datasets. Our findings highlight the challenges of applying existing bias mitigation methods to linguistically complex languages, underscoring the need for more inclusive approaches in the development of multilingual NLP.
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。
