Saved in:
Bibliographic Details
Main Authors: Pérez, Juan Manuel, Miguel, Paula, Cotik, Viviana
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.12174
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914974234836992
author Pérez, Juan Manuel
Miguel, Paula
Cotik, Viviana
author_facet Pérez, Juan Manuel
Miguel, Paula
Cotik, Viviana
contents Hate speech detection deals with many language variants, slang, slurs, expression modalities, and cultural nuances. This outlines the importance of working with specific corpora, when addressing hate speech within the scope of Natural Language Processing, recently revolutionized by the irruption of Large Language Models. This work presents a brief analysis of the performance of large language models in the detection of Hate Speech for Rioplatense Spanish. We performed classification experiments leveraging chain-of-thought reasoning with ChatGPT 3.5, Mixtral, and Aya, comparing their results with those of a state-of-the-art BERT classifier. These experiments outline that, even if large language models show a lower precision compared to the fine-tuned BERT classifier and, in some cases, they find hard-to-get slurs or colloquialisms, they still are sensitive to highly nuanced cases (particularly, homophobic/transphobic hate speech). We make our code and models publicly available for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12174
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish
Pérez, Juan Manuel
Miguel, Paula
Cotik, Viviana
Computation and Language
Hate speech detection deals with many language variants, slang, slurs, expression modalities, and cultural nuances. This outlines the importance of working with specific corpora, when addressing hate speech within the scope of Natural Language Processing, recently revolutionized by the irruption of Large Language Models. This work presents a brief analysis of the performance of large language models in the detection of Hate Speech for Rioplatense Spanish. We performed classification experiments leveraging chain-of-thought reasoning with ChatGPT 3.5, Mixtral, and Aya, comparing their results with those of a state-of-the-art BERT classifier. These experiments outline that, even if large language models show a lower precision compared to the fine-tuned BERT classifier and, in some cases, they find hard-to-get slurs or colloquialisms, they still are sensitive to highly nuanced cases (particularly, homophobic/transphobic hate speech). We make our code and models publicly available for future research.
title Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish
topic Computation and Language
url https://arxiv.org/abs/2410.12174