Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage

The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure. One notable capability of LLMs is their ability to form associations between different pieces of information, but this raises concerns when it comes to personally identifiable information (PII). This paper delves into the association capabilities of language models, aiming to uncover the factors that influence their proficiency in associating information. Our study reveals that as models scale up, …

advancement applications capabilities cs.ai cs.cl cs.cr data data exposure exposure information language language models large llms privacy private private data