Instant Personalized Large Language Model Adaptation via Hypernetwork

2025-10-17

AI Summary

Existing parameter-efficient fine-tuning (PEFT) methods require per-user adapter training, incurring high computational overhead and hindering real-time personalization. To address this, we propose Profile-to-PEFT: an end-to-end trainable hypernetwork that directly maps user profiles to full LoRA adapter parameters—enabling zero-shot, on-the-fly personalization without user-side training. Our framework supports localized deployment and privacy-preserving inference, while demonstrating strong generalization to unseen users and diverse behavioral patterns. Experiments show that Profile-to-PEFT outperforms prompt-based learning and single-user fine-tuning in personalization quality, maintaining robustness while drastically reducing deployment computational cost. This advances the efficiency, scalability, and practicality of large language model personalization at scale.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm, require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates. We introduce Profile-to-PEFT, a scalable framework that employs a hypernetwork, trained end-to-end, to map a user's encoded profile directly to a full set of adapter parameters (e.g., LoRA), eliminating per-user training at deployment. This design enables instant adaptation, generalization to unseen users, and privacy-preserving local deployment. Experimental results demonstrate that our method outperforms both prompt-based personalization and OPPU while using substantially fewer computational resources at deployment. The framework exhibits strong generalization to out-of-distribution users and maintains robustness across varying user activity levels and different embedding backbones. The proposed Profile-to-PEFT framework enables efficient, scalable, and adaptive LLM personalization suitable for large-scale applications.

Problem

• Eliminates per-user training for personalized LLM adaptation
• Enables instant model updates using hypernetwork-generated parameters
• Achieves scalable personalization while preserving user privacy

Innovation

• Hypernetwork maps user profiles to adapter parameters
• Eliminates per-user training for instant adaptation
• Enables scalable personalization with fewer computational resources