English

From BERT to Qwen: Hate Detection across architectures

Computation and Language 2025-07-15 v1 Machine Learning

Abstract

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).

Keywords

Cite

@article{arxiv.2507.10468,
  title  = {From BERT to Qwen: Hate Detection across architectures},
  author = {Ariadna Mon and Saúl Fenollosa and Jon Lecumberri},
  journal= {arXiv preprint arXiv:2507.10468},
  year   = {2025}
}

Comments

4 pages, 5 figures. EE-559 Deep Learning course project (Group 11)

R2 v1 2026-07-01T04:00:25.507Z