PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation

TL;DR

PRISP is a lightweight, privacy-preserving personalization method for large language models that efficiently adapts to individual users with limited data and resources, outperforming prior approaches.

Contribution

PRISP introduces a novel Text-to-LoRA hypernetwork for privacy-safe, efficient personalization tailored to resource-constrained, data-scarce scenarios.

Findings

Achieves strong performance on LaMP benchmark

Reduces computational overhead significantly

Eliminates privacy risks in personalization

Abstract

Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abundant settings, often incurring privacy risks. In contrast, realistic personalization typically occurs after deployment under (i) extremely limited user data, (ii) constrained computational resources, and (iii) strict privacy requirements. We propose PRISP, a lightweight and privacy-safe personalization framework tailored to these constraints. PRISP leverages a Text-to-LoRA hypernetwork to generate task-aware LoRA parameters from task descriptions, and enables efficient user personalization by optimizing a small subset of task-aware LoRA parameters together with minimal additional modules using few-shot user data. Experiments on a few-shot variant of the LaMP benchmark demonstrate that PRISP achieves strong overall performance compared to prior approaches, while reducing computational overhead and eliminating privacy risks.