Word-level Annotation of GDPR Transparency Compliance in Privacy Policies using Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cory, Thomas, Rieder, Wolf, Krämer, Julia, Raschke, Philip, Herbke, Patrick, Küpper, Axel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918216415051776
author Cory, Thomas
Rieder, Wolf
Krämer, Julia
Raschke, Philip
Herbke, Patrick
Küpper, Axel
author_facet Cory, Thomas
Rieder, Wolf
Krämer, Julia
Raschke, Philip
Herbke, Patrick
Küpper, Axel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10727
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Word-level Annotation of GDPR Transparency Compliance in Privacy Policies using Large Language Models
Cory, Thomas
Rieder, Wolf
Krämer, Julia
Raschke, Philip
Herbke, Patrick
Küpper, Axel
Computation and Language
Artificial Intelligence
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.
title Word-level Annotation of GDPR Transparency Compliance in Privacy Policies using Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.10727