# From BERT to Qwen: Hate Detection across architectures

arXiv: https://arxiv.org/abs/2507.10468 · HTML: https://mlsanity.com/paper/2507.10468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model](https://mlsanity.com/paper/2111.01515/) (2021)
- [MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection](https://mlsanity.com/paper/2401.06526/) (2024)

## Abstract (arXiv)

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).