3 papers
cs.CR2025
Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
Elena Sofia Ruzzetti, Giancarlo A. Xompero, Davide Venditti +1
Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, co…
cs.CL2025
MeMo: Towards Language Models with Associative Memory Mechanisms
Fabio Massimo Zanzotto, Elena Sofia Ruzzetti, Giancarlo A. Xompero +6
Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture…
cs.CL2024
Enhancing Data Privacy in Large Language Models through Private Association Editing
Davide Venditti, Elena Sofia Ruzzetti, Giancarlo A. Xompero +4
Large language models (LLMs) require a significant redesign in solutions to preserve privacy in data-intensive applications due to their text-generation capabilities. Indeed, LLMs…