How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review

TL;DR

This paper evaluates how privacy-savvy large language models are by applying a Privacy Technical Review (PTR) framework to privacy tasks. It introduces a PTR workflow and benchmarks multiple LLMs on privacy information extraction, key point detection, and domain-specific QA against policy and regulation texts. Results show near-perfect PIE with modern LLMs and strong KPD, but QA performance and full regulatory alignment still lag behind ideal compliance, underscoring gaps in current models. The findings offer concrete recommendations for improving privacy-aware LLMs and integrating them with legal and regulatory requirements to better safeguard user privacy in real-world deployments.

Abstract

The recent advances in large language models (LLMs) have significantly expanded their applications across various fields such as language generation, summarization, and complex question answering. However, their application to privacy compliance and technical privacy reviews remains under-explored, raising critical concerns about their ability to adhere to global privacy standards and protect sensitive user data. This paper seeks to address this gap by providing a comprehensive case study evaluating LLMs' performance in privacy-related tasks such as privacy information extraction (PIE), legal and regulatory key point detection (KPD), and question answering (QA) with respect to privacy policies and data protection regulations. We introduce a Privacy Technical Review (PTR) framework, highlighting its role in mitigating privacy risks during the software development life-cycle. Through an empirical assessment, we investigate the capacity of several prominent LLMs, including BERT, GPT-3.5, GPT-4, and custom models, in executing privacy compliance checks and technical privacy reviews. Our experiments benchmark the models across multiple dimensions, focusing on their precision, recall, and F1-scores in extracting privacy-sensitive information and detecting key regulatory compliance points. While LLMs show promise in automating privacy reviews and identifying regulatory discrepancies, significant gaps persist in their ability to fully comply with evolving legal standards. We provide actionable recommendations for enhancing LLMs' capabilities in privacy compliance, emphasizing the need for robust model improvements and better integration with legal and regulatory requirements. This study underscores the growing importance of developing privacy-aware LLMs that can both support businesses in compliance efforts and safeguard user privacy rights.

Figures (4)

• Figure 1: Illustration of software development life-cycle (SDLC) process.
• Figure 2: Illustration of privacy technical review in business process.
• Figure 3: Illustration of privacy technical review process.
• Figure 4: Word cloud of QA dataset.