PRvL：量化大语言模型在个人身份信息脱敏中的能力与风险

摘要

从非结构化文本中删除个人身份信息（PII）对于确保受监管领域的数据隐私至关重要。虽然早期方法依赖于基于规则的系统及特定领域的命名实体识别（NER）模型，但这些方法难以跨格式和上下文进行泛化。大型语言模型（LLMs）的最新进展提供了一个有前景的替代方案，然而架构和训练选择对信息删除性能的影响仍未被充分探索。LLMs在需要上下文语言理解的任务中表现出色，包括自由文本中的PII删除。先前的研究表明，通过适当的适配，LLMs可以成为有效的上下文隐私学习器。尽管如此，架构和训练选择对PII删除的具体影响仍待深入研究。在本研究中，我们对LLMs作为隐私保护的PII删除系统进行了全面分析，评估了多种LLM架构和训练策略在PII删除中的有效性。我们的分析衡量了删除性能、语义保持及PII泄露，并将这些结果与延迟和计算成本进行了对比。研究结果为配置准确、高效且注重隐私的基于LLM的删除器提供了实用指导。为了支持可重复性和实际部署，我们发布了PRvL，一个开源的精调模型套件及通用PII删除评估工具。PRvL完全基于开源LLMs构建，支持多种推理设置，以确保灵活性和合规性。它设计为易于针对不同领域定制，并能在安全、自我管理的环境中完全运行，使数据所有者无需依赖第三方服务或在其基础设施之外暴露敏感内容即可执行删除操作。

English

Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-based systems and domain-specific Named Entity Recognition (NER) models, these methods fail to generalize across formats and contexts. Recent advances in Large Language Models (LLMs) offer a promising alternative, yet the effect of architectural and training choices on redaction performance remains underexplored. LLMs have demonstrated strong performance in tasks that require contextual language understanding, including the redaction of PII in free-form text. Prior work suggests that with appropriate adaptation, LLMs can become effective contextual privacy learners. However, the consequences of architectural and training choices for PII Redaction remain underexplored. In this work, we present a comprehensive analysis of LLMs as privacy-preserving PII Redaction systems. We evaluate a range of LLM architectures and training strategies for their effectiveness in PII Redaction. Our analysis measures redaction performance, semantic preservation, and PII leakage, and compares these outcomes against latency and computational cost. The results provide practical guidance for configuring LLM-based redactors that are accurate, efficient, and privacy-aware. To support reproducibility and real-world deployment, we release PRvL, an open-source suite of fine-tuned models, and evaluation tools for general-purpose PII Redaction. PRvL is built entirely on open-source LLMs and supports multiple inference settings for flexibility and compliance. It is designed to be easily customized for different domains and fully operable within secure, self-managed environments. This enables data owners to perform redactions without relying on third-party services or exposing sensitive content beyond their own infrastructure.

PRvL：量化大语言模型在个人身份信息脱敏中的能力与风险

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

摘要

Support