Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hee, Ming Shan, Kumaresan, Aditi, Lee, Roy Ka-Wei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909340087091200
author Hee, Ming Shan
Kumaresan, Aditi
Lee, Roy Ka-Wei
author_facet Hee, Ming Shan
Kumaresan, Aditi
Lee, Roy Ka-Wei
contents The widespread presence of hate speech on the internet, including formats such as text-based tweets and vision-language memes, poses a significant challenge to digital platform safety. Recent research has developed detection models tailored to specific modalities; however, there is a notable gap in transferring detection capabilities across different formats. This study conducts extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities. Our findings demonstrate that text-based hate speech examples can significantly enhance the classification accuracy of vision-language hate speech. Moreover, text-based demonstrations outperform vision-language demonstrations in few-shot learning settings. These results highlight the effectiveness of cross-modality knowledge transfer and offer valuable insights for improving hate speech detection systems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning
Hee, Ming Shan
Kumaresan, Aditi
Lee, Roy Ka-Wei
Computation and Language
The widespread presence of hate speech on the internet, including formats such as text-based tweets and vision-language memes, poses a significant challenge to digital platform safety. Recent research has developed detection models tailored to specific modalities; however, there is a notable gap in transferring detection capabilities across different formats. This study conducts extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities. Our findings demonstrate that text-based hate speech examples can significantly enhance the classification accuracy of vision-language hate speech. Moreover, text-based demonstrations outperform vision-language demonstrations in few-shot learning settings. These results highlight the effectiveness of cross-modality knowledge transfer and offer valuable insights for improving hate speech detection systems.
title Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning
topic Computation and Language
url https://arxiv.org/abs/2410.05600