解释很重要：利用定义与语义扩展进行性别歧视检测
Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection
AI总结：
本文针对在线性别歧视检测中的数据稀疏和类别不平衡问题，提出基于定义的数据增强和上下文语义扩展两种提示增强方法，并结合多模型集成策略，在 EDOS 数据集上取得最优性能。
摘要：
在线内容中的性别歧视检测仍然是一个未解决的问题，因为有害语言对女性和边缘群体造成不成比例的影响。尽管已经开发了用于性别歧视检测的自动化系统，但它们仍面临两个关键挑战：数据稀疏性和性别歧视语言的细微性。即使在大型且经过精心整理的数据集（如可解释在线性别歧视检测数据集 EDOS）中，严重的类别不平衡也阻碍了模型泛化。此外，细粒度类别之间重叠且模糊的边界带来了大量标注者分歧，反映出解释性别歧视细微表达上的困难。为应对这些挑战，我们提出了两种基于提示的数据增强技术：基于定义的数据增强（Definition-based Data Augmentation，DDA），利用类别特定定义生成语义对齐的合成示例；以及上下文语义扩展（Contextual Semantic Expansion，CSE），通过为示例补充任务特定的语义特征来针对系统性模型错误。为进一步提高细粒度分类的可靠性，我们引入了一种集成策略，通过聚合多个语言模型的互补视角来解决预测并列问题。我们在 EDOS 数据集上的实验评估在所有任务上均展示了最先进的性能，其中二分类（任务 A）的宏 F1 提升了 1.5 个点，细粒度分类（任务 C）的宏 F1 提升了 4.1 个点。
英文摘要：
The detection of sexism in online content remains an open problem, as harmful language disproportionately affects women and marginalized groups. While automated systems for sexism detection have been developed, they still face two key challenges: data sparsity and the nuanced nature of sexist language. Even in large, well-curated datasets like the Explainable Detection of Online Sexism (EDOS), severe class imbalance hinders model generalization. Additionally, the overlapping and ambiguous boundaries of fine-grained categories introduce substantial annotator disagreement, reflecting the difficulty of interpreting nuanced expressions of sexism. To address these challenges, we propose two prompt-based data augmentation techniques: Definition-based Data Augmentation (DDA), which leverages category-specific definitions to generate semantically-aligned synthetic examples, and Contextual Semantic Expansion (CSE), which targets systematic model errors by enriching examples with task-specific semantic features. To further improve reliability in fine-grained classification, we introduce an ensemble strategy that resolves prediction ties by aggregating complementary perspectives from multiple language models. Our experimental evaluation on the EDOS dataset demonstrates state-of-the-art performance across all tasks, with notable improvements of macro F1 by 1.5 points for binary classification (Task A) and 4.1 points for fine-grained classification (Task C).
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。
