基于大型语言模型的GDPR透明性合规性隐私政策词级注释
Word-level Annotation of GDPR Transparency Compliance in Privacy Policies using Large Language Models
AI总结：
本文提出基于LLM的隐私政策词级注释方法，用于评估GDPR透明性合规性，通过模块化管道和双层评估提升注释准确性。
摘要：
确保与个人信息相关的数据实践的透明性是通用数据保护条例（GDPR）的核心要求。然而，大规模合规性评估仍然具有挑战性，因为隐私政策语言的复杂性和多样性。手动审计劳动强度大且不一致，而当前的自动化方法往往缺乏捕捉细微透明披露所需粒度的能力。在本文中，我们提出了一种模块化的基于大型语言模型（LLM）的管道，用于对隐私政策进行细粒度的词级注释，以符合GDPR透明性要求。我们的方法整合了LLM驱动的注释、段落级分类、检索增强生成以及自我纠正机制，以在21个GDPR衍生的透明性要求上提供可扩展的、上下文感知的注释。为了支持实证评估，我们编译了一个包含703,791个英语隐私政策的语料库，并根据一个全面的、符合GDPR的注释方案生成了200个人工注释的基准样本。我们提出了一种双层评估方法，捕捉段落级分类和跨度级注释质量，并在两种注释方案上对七种最先进的LLM进行了比较分析，包括广泛使用的OPP-115数据集。我们的评估结果表明，分解注释任务并整合针对性检索和分类组件显著提高了注释准确性，尤其是在结构良好的要求上。我们的工作为在大规模上推进自动化透明性合规性评估提供了新的实证资源和方法论基础。
英文摘要：
Ensuring transparency of data practices related to personal information is a core requirement of the General Data Protection Regulation (GDPR). However, large-scale compliance assessment remains challenging due to the complexity and diversity of privacy policy language. Manual audits are labour-intensive and inconsistent, while current automated methods often lack the granularity required to capture nuanced transparency disclosures. In this paper, we present a modular large language model (LLM)-based pipeline for fine-grained word-level annotation of privacy policies with respect to GDPR transparency requirements. Our approach integrates LLM-driven annotation with passage-level classification, retrieval-augmented generation, and a self-correction mechanism to deliver scalable, context-aware annotations across 21 GDPR-derived transparency requirements. To support empirical evaluation, we compile a corpus of 703,791 English-language privacy policies and generate a ground-truth sample of 200 manually annotated policies based on a comprehensive, GDPR-aligned annotation scheme. We propose a two-tiered evaluation methodology capturing both passage-level classification and span-level annotation quality and conduct a comparative analysis of seven state-of-the-art LLMs on two annotation schemes, including the widely used OPP-115 dataset. The results of our evaluation show that decomposing the annotation task and integrating targeted retrieval and classification components significantly improve annotation accuracy, particularly for well-structured requirements. Our work provides new empirical resources and methodological foundations for advancing automated transparency compliance assessment at scale.
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。
