GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
Wei Fan, Haoran Li, Zheye Deng, Weiqi Wang, Yangqiu Song

TL;DR
GoldCoin is a novel framework that uses contextual integrity theory to ground large language models in privacy laws, improving their ability to identify privacy violations in complex social contexts and real court cases.
Contribution
It introduces a new approach leveraging synthetic scenarios based on privacy laws to enhance LLM understanding of privacy violations within social contexts.
Findings
GoldCoin significantly improves LLM performance in recognizing privacy risks.
The framework surpasses baseline models on judicial privacy tasks.
Synthetic scenario generation aids in legal comprehension of privacy issues.
Abstract
Privacy issues arise prominently during the inappropriate transmission of information between entities. Existing research primarily studies privacy by exploring various privacy attacks, defenses, and evaluations within narrowly predefined patterns, while neglecting that privacy is not an isolated, context-free concept limited to traditionally sensitive data (e.g., social security numbers), but intertwined with intricate social contexts that complicate the identification and analysis of potential privacy violations. The advent of Large Language Models (LLMs) offers unprecedented opportunities for incorporating the nuanced scenarios outlined in privacy laws to tackle these complex privacy issues. However, the scarcity of open-source relevant case studies restricts the efficiency of LLMs in aligning with specific legal statutes. To address this challenge, we introduce a novel framework,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsHate Speech and Cyberbullying Detection · Privacy, Security, and Data Protection · Artificial Intelligence in Law
