# Efficient Hate Speech Detection: A Three-Layer LoRA-Tuned BERTweet Framework

arXiv: https://arxiv.org/abs/2511.06051 · HTML: https://mlsanity.com/paper/2511.06051/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Builds on (most cited first, 6 of 6)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets](https://mlsanity.com/paper/2404.17874/) (2024)
- [MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection](https://mlsanity.com/paper/2401.06526/) (2024)
- [Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach](https://mlsanity.com/paper/2508.07063/) (2025)
- [A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English](https://mlsanity.com/paper/2504.08609/) (2025)

## Abstract (arXiv)

This paper addresses the critical challenge of developing computationally efficient hate speech detection systems that maintain competitive performance while being practical for real-time deployment. We propose a novel three-layer framework that combines rule-based pre-filtering with a parameter-efficient LoRA-tuned BERTweet model and continuous learning capabilities. Our approach achieves 0.85 macro F1 score - representing 94% of the performance of state-of-the-art large language models like SafePhi (Phi-4 based) while using a base model that is 100x smaller (134M vs 14B parameters). Compared to traditional BERT-based approaches with similar computational requirements, our method demonstrates superior performance through strategic dataset unification and optimized fine-tuning. The system requires only 1.87M trainable parameters (1.37% of full fine-tuning) and trains in approximately 2 hours on a single T4 GPU, making robust hate speech detection accessible in resource-constrained environments while maintaining competitive accuracy for real-world deployment.