arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15757cs.CLcs.AI
收藏

超越二元分类:在社交媒体视频中检测细粒度性别歧视

Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos

CLiC – Language and Computing Center, University of Barcelona(巴塞罗那大学语言与计算中心);Department of Computer Science, University of Copenhagen(哥本哈根大学计算机科学系)

Laura De Grazia, Danae Sánchez Villegas, Desmond Elliott, Mireia Farrús, Mariona Taulé

AI总结:

本文提出FineMuSe数据集和层级分类法,评估LLM在细粒度性别歧视检测中的表现,发现多模态LLM在识别细微性别歧视方面表现优异,但在捕捉视觉线索中的多重歧视类型时存在困难。

摘要:

在线性别歧视以多种形式出现,这使得其检测具有挑战性。尽管自动化工具可以增强对性别歧视内容的识别,但它们通常局限于二元分类。因此,由于缺乏细粒度、上下文敏感的标签,更微妙的性别歧视表现可能仍无法被检测到。为了解决这一问题,我们做出了以下贡献:(1)我们提出了FineMuSe,一个包含二元和细粒度标注的新的多模态性别歧视检测西班牙语数据集;(2)我们介绍了一个涵盖性别歧视形式、非性别歧视以及讽刺和幽默修辞手法的综合性层级分类法;(3)我们评估了多种LLM在二元和细粒度性别歧视检测中的表现。我们的发现表明,多模态LLM在识别微妙的性别歧视形式方面与人类标注者表现相当;然而,当这些性别歧视类型通过视觉线索传达时,它们在捕捉共现的性别歧视类型时却面临困难。

英文摘要:

Online sexism appears in various forms, which makes its detection challenging. Although automated tools can enhance the identification of sexist content, they are often restricted to binary classification. Consequently, more subtle manifestations of sexism may remain undetected due to the lack of fine-grained, context-sensitive labels. To address this issue, we make the following contributions: (1) we present FineMuSe, a new multimodal sexism detection dataset in Spanish that includes both binary and fine-grained annotations; (2) we introduce a comprehensive hierarchical taxonomy that encompasses forms of sexism, non-sexism, and rhetorical devices of irony and humor; and (3) we evaluate a wide range of LLMs for both binary and fine-grained sexism detection. Our findings indicate that multimodal LLMs perform competitively with human annotators in identifying nuanced forms of sexism; however, they struggle to capture co-occurring sexist types when these are conveyed through visual cues.

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。

↑