Bielik Guard：高效的波兰语安全分类器用于LLM内容审核
Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
AI总结：
Bielik Guard通过高效波兰语安全分类器提升LLM内容审核效果，0.5B模型在F1分数上表现最佳，0.1B模型在效率与低误报率上优于现有方案。
摘要：
随着大型语言模型（LLMs）在波兰语应用中的日益普及，高效且准确的内容安全分类器的需求变得至关重要。我们介绍了Bielik Guard，一种紧凑的波兰语安全分类器家族，包含两种模型变体：基于MMLW-RoBERTa-base的0.1B参数模型和基于PKOBP/polish-roberta-8k的0.5B参数模型。这些模型在6,885个波兰文本的社区标注数据集上进行微调，用于对五类安全内容进行分类：仇恨/攻击、粗俗语言、性内容、犯罪和自残。我们的评估表明，两种模型在多个基准上均表现出色。0.5B变体在测试集上实现了0.791（微）和0.785（宏）的F1分数，是整体判别能力最佳的模型，而0.1B变体则展示了卓越的效率。值得注意的是，Bielik Guard 0.1B v1.1在实际用户提示中实现了77.65%的精度和极低的误报率（0.63%），优于HerBERT-PL-Guard（31.55%精度，4.70% FPR），尽管两者模型大小相同。这些模型公开可用，并旨在提供适当的响应而非简单的内容阻止，尤其针对自残等敏感类别。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
