用小模型实现高效仇恨言论检测，性能接近大模型。
Efficient Hate Speech Detection: A Three-Layer LoRA-Tuned BERTweet Framework
- 三层次框架：规则预过滤+LoRA微调BERTweet+持续学习
- 仅134M参数达0.85宏F1，为大模型的94%
- 训练仅需2小时，适合资源受限环境部署
本文针对计算高效仇恨言论检测系统的设计挑战，提出一种新型三层框架，结合规则预过滤、参数高效的LoRA-tuned BERTweet模型与持续学习能力。该方法在保持竞争力表现的同时，显著降低计算开销：模型仅134M参数（相较14B参数的SafePhi模型缩小100倍），达到0.85宏F1分数，为先进大模型性能的94%。相比同类计算量的BERT基线方法，通过数据集统一与优化微调策略实现更优效果。系统仅需187万可训练参数（占全量微调的1.37%），在单张T4 GPU上约2小时即可完成训练，使高精度仇恨言论检测在资源受限场景中具备可行性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。