PRvL：量化大型語言模型於個人識別資訊遮蔽之能力與風險

摘要

從非結構化文本中刪除個人識別資訊（PII）對於確保受監管領域的數據隱私至關重要。雖然早期方法依賴於基於規則的系統和特定領域的命名實體識別（NER）模型，但這些方法無法跨格式和上下文進行泛化。大型語言模型（LLMs）的最新進展提供了一種有前景的替代方案，然而，架構和訓練選擇對刪除性能的影響仍未得到充分探索。LLMs在需要上下文語言理解的任務中表現出色，包括在自由形式文本中刪除PII。先前的研究表明，通過適當的適應，LLMs可以成為有效的上下文隱私學習者。然而，架構和訓練選擇對PII刪除的影響仍未得到充分探索。在本研究中，我們對LLMs作為隱私保護的PII刪除系統進行了全面分析。我們評估了一系列LLM架構和訓練策略在PII刪除中的有效性。我們的分析測量了刪除性能、語義保留和PII洩漏，並將這些結果與延遲和計算成本進行比較。結果為配置準確、高效且具有隱私意識的基於LLM的刪除器提供了實用指導。為了支持可重現性和實際部署，我們發布了PRvL，這是一個開源的微調模型套件和通用PII刪除的評估工具。PRvL完全基於開源LLMs構建，並支持多種推理設置以實現靈活性和合規性。它旨在輕鬆定制以適應不同領域，並完全在安全、自我管理的環境中運行。這使得數據所有者能夠在不依賴第三方服務或將敏感內容暴露於自身基礎設施之外的情況下執行刪除操作。

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：量化大型語言模型於個人識別資訊遮蔽之能力與風險

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

摘要

Support