轻量级波兰语安全分类器，精准识别五类敏感内容
Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
- 基于MMLW-RoBERTa和Polish-RoBERTa构建0.1B/0.5B小模型
- 0.1B版在真实用户输入中实现77.65%精确率与0.63%误报率
- 专为敏感内容设计响应而非直接屏蔽，适合实际应用
随着大语言模型在波兰语应用中的普及，高效准确的内容安全分类需求日益迫切。本文提出Bielik Guard，一个包含两个版本的紧凑波兰语安全分类器：基于MMLW-RoBERTa-base的0.1B参数模型，以及基于PKOBP/polish-roberta-8k的0.5B参数模型。两者均在包含6,885条波兰语文本的社区标注数据集上微调，可对仇恨/攻击、粗俗、性内容、犯罪和自残五类内容进行分类。评估显示，0.5B版本在测试集上取得0.791（micro）和0.785（macro）的F1分数，表现最优；而0.1B版本展现出卓越效率。值得注意的是，Bielik Guard 0.1B v1.1在真实用户提示中实现77.65%的精度和0.63%的极低误报率，优于同规模的HerBERT-PL-Guard（31.55%精度，4.70%误报率）。模型已公开，旨在提供适当回应而非简单屏蔽，尤其针对自残等敏感类别。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) become increasingly deployed in Polish language applications, the need for efficient and accurate content safety classifiers has become paramount. We present Bielik Guard, a family of compact Polish language safety classifiers comprising two model variants: a 0.1B parameter model based on MMLW-RoBERTa-base and a 0.5B parameter model based on PKOBP/polish-roberta-8k. Fine-tuned on a community-annotated dataset of 6,885 Polish texts, these models classify content across five safety categories: Hate/Aggression, Vulgarities, Sexual Content, Crime, and Self-Harm. Our evaluation demonstrates that both models achieve strong performance on multiple benchmarks. The 0.5B variant offers the best overall discrimination capability with F1 scores of 0.791 (micro) and 0.785 (macro) on the test set, while the 0.1B variant demonstrates exceptional efficiency. Notably, Bielik Guard 0.1B v1.1 achieves superior precision (77.65%) and very low false positive rate (0.63%) on real user prompts, outperforming HerBERT-PL-Guard (31.55% precision, 4.70% FPR) despite identical model size. The models are publicly available and designed to provide appropriate responses rather than simple content blocking, particularly for sensitive categories like self-harm.
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。