Work

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

Year: 2026

Type: conference-paper

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 (Privacy-Safe Few-Shot Personalization), a lightweight 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.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-long.1146

Authors: Junho Park, Dohoon Kim, Taesup Moon

Institution: Seoul National University

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid