Saved in:
Bibliographic Details
Main Authors: De Grazia, Laura, Villegas, Danae Sánchez, Elliott, Desmond, Farrús, Mireia, Taulé, Mariona
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15757
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917278334844928
author De Grazia, Laura
Villegas, Danae Sánchez
Elliott, Desmond
Farrús, Mireia
Taulé, Mariona
author_facet De Grazia, Laura
Villegas, Danae Sánchez
Elliott, Desmond
Farrús, Mireia
Taulé, Mariona
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15757
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos
De Grazia, Laura
Villegas, Danae Sánchez
Elliott, Desmond
Farrús, Mireia
Taulé, Mariona
Computation and Language
Artificial Intelligence
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.
title Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.15757