← Search

Giancarlo A. Xompero

2 accepted papers

2025

Position Paper: MeMo: Towards Language Models with Associative Memory Mechanisms

ACL 2025finding

Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this position/theory paper, we propose a paradigm shift by designing an architecture to memorize text directly, bearing in mind the principle that memorization precedes learning. We introd…

Cited by 0SourcePDFScholar
2025

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models

ACL 2025long

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, consequently, not leaked. In this paper, we introduce Private Memorization Editing (PME), an approach for preventing priva…