混合规则与大模型，实现13种低资源语言的高效隐私信息检测
An Evaluation Study of Hybrid Methods for Multilingual PII Detection
- 用规则匹配+上下文感知大模型混合方式，无需重训练
- 在13个低资源语言上加权F1提升82%（相比微调NER）
- 适合需要多语言合规检测的隐私保护系统
个人身份信息（PII）检测对隐私合规至关重要，但在低资源语言中仍具挑战，主要因语言多样性及标注数据有限。我们提出RECAP，一种结合确定性正则表达式与上下文感知大语言模型的混合框架，可跨13个低资源语区实现可扩展的PII检测。其模块化设计支持超过300种实体类型且无需重新训练，通过三阶段精炼流程完成消歧与过滤。在nervaluate基准测试中，该系统加权F1得分比微调的命名实体识别模型高82%，比零样本大模型高17%。本工作为合规应用提供了可扩展、可适应的高效PII检测方案。
原文摘要 · Abstract (English)
The detection of Personally Identifiable Information (PII) is critical for privacy compliance but remains challenging in low-resource languages due to linguistic diversity and limited annotated data. We present RECAP, a hybrid framework that combines deterministic regular expressions with context-aware large language models (LLMs) for scalable PII detection across 13 low-resource locales. RECAP's modular design supports over 300 entity types without retraining, using a three-phase refinement pipeline for disambiguation and filtering. Benchmarked with nervaluate, our system outperforms fine-tuned NER models by 82% and zero-shot LLMs by 17% in weighted F1-score. This work offers a scalable and adaptable solution for efficient PII detection in compliance-focused applications.
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。