Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM

2026-09-04

AI Summary

本文针对个性化调查响应预测问题，提出Aplaud框架，通过低秩分解和用户特定校正实现轻量级、可扩展的大型语言模型个性化。

Abstract

In this paper, we study the problem of personalized survey response prediction using fine-tuned large language models (LLMs). This task poses unique challenges: limited per-user training data, scalability of model storage, and the need to exploit shared structure across survey questions. To address these issues, we propose Aplaud (Adaptive Personalized Low-rank and User-specific Nested Decomposition), a lightweight and scalable framework for LLM personalization. Aplaud extends the LoRA paradigm by separating adaptation into a frozen, shared low-rank basis and a compact user-specific correction, augmented with a rank-one residual for finer personalization. To further reduce per-user parameter cost and mitigate overfitting, the correction matrix can be factorized into an even lower-rank form. Empirical results demonstrate that Aplaud achieves efficient, scalable personalization across users while outperforming state-of-the-art LoRA-based personalized LLM approaches in both generalization and inference efficiency.

Problem

• Personalized Survey Response Prediction
• Large Language Models
• Limited Training Data
• Model Storage Scalability
• Shared Structure Across Questions

Innovation

• Adaptive Personalized Low-Rank Decomposition
• User-Specific Correction
• Rank-One Residual
• Scalable Personalization
• Parameter Cost Reduction