Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mon, Ariadna, Fenollosa, Saúl, Lecumberri, Jon
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.10468
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911054811889664
author Mon, Ariadna
Fenollosa, Saúl
Lecumberri, Jon
author_facet Mon, Ariadna
Fenollosa, Saúl
Lecumberri, Jon
contents Online platforms struggle to curb hate speech without over-censoring legitimate discourse. Early bidirectional transformer encoders made big strides, but the arrival of ultra-large autoregressive LLMs promises deeper context-awareness. Whether this extra scale actually improves practical hate-speech detection on real-world text remains unverified. Our study puts this question to the test by benchmarking both model families, classic encoders and next-generation LLMs, on curated corpora of online interactions for hate-speech detection (Hate or No Hate).
format Preprint
id arxiv_https___arxiv_org_abs_2507_10468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From BERT to Qwen: Hate Detection across architectures
Mon, Ariadna
Fenollosa, Saúl
Lecumberri, Jon
Computation and Language
Machine Learning
Online platforms struggle to curb hate speech without over-censoring legitimate discourse. Early bidirectional transformer encoders made big strides, but the arrival of ultra-large autoregressive LLMs promises deeper context-awareness. Whether this extra scale actually improves practical hate-speech detection on real-world text remains unverified. Our study puts this question to the test by benchmarking both model families, classic encoders and next-generation LLMs, on curated corpora of online interactions for hate-speech detection (Hate or No Hate).
title From BERT to Qwen: Hate Detection across architectures
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2507.10468