GLiNER2-PII：一种多语言的个人可识别信息提取模型
GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction
AI总结：
GLiNER2-PII通过构建多语言合成语料库，实现了对42种PII实体类型的高效识别，在SPY基准测试中取得最高span-level F1分数。
摘要：
可靠检测个人可识别信息（PII）在现代数据处理系统中日益重要，但该任务仍然困难：PII跨度异质性、地域依赖性、语境敏感性且常嵌入噪声或半结构化文档。我们提出了GLiNER2-PII，一个基于GLiNER2的0.3B参数模型，能够识别42种PII实体类型。然而，训练此类系统受限于共享标注数据的稀缺性和大规模收集真实PII的隐私风险。为解决此挑战，我们构建了一个包含4910个标注文本的多语言合成语料库，使用约束驱动生成管道生成多样且真实的跨语言、领域、格式和实体分布的例子。在具有挑战性的SPY基准测试中，GLiNER2-PII在五个对比系统中取得最高span-level F1分数，包括OpenAI Privacy Filter和三个GLiNER基检测器。我们公开发布该模型以支持进一步研究和开放PII检测系统的实际部署。
英文摘要：
Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains difficult: PII spans are heterogeneous, locale-dependent, context-sensitive, and often embedded in noisy or semi-structured documents. We present GLiNER2-PII, a small 0.3B-parameter model adapted from GLiNER2 and designed to recognize a broad taxonomy of 42 PII entity types at character-span resolution. Training such systems, however, is constrained by the scarcity of shareable annotated data and the privacy risks associated with collecting real PII at scale. To address this challenge, we construct a multilingual synthetic corpus of 4,910 annotated texts using a constraint-driven generation pipeline that produces diverse, realistic examples across languages, domains, formats, and entity distributions. On the challenging SPY benchmark, GLiNER2-PII achieves the highest span-level F1 among five compared systems, including OpenAI Privacy Filter and three GLiNER-based detectors. We publicly release the model on Hugging Face to support further research and practical deployment of open PII detection systems.
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。
