Aplaud通过低秩分解实现用户个性化大模型，兼顾高效与精准。
Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM
- 将模型微调拆分为共享低秩基和用户专属修正项，提升可扩展性。
- 在有限数据下仍保持良好泛化能力，推理效率优于现有方法。
- 适合需要低成本个性化部署的场景，如问卷回复预测系统。
本文研究基于微调大语言模型（LLM）的个性化问卷回复预测问题。该任务面临三大挑战：每位用户训练数据有限、模型存储成本高，以及需利用跨问题的共享结构。为此，我们提出Aplaud（自适应个性化低秩与用户特定嵌套分解），一种轻量且可扩展的LLM个性化框架。Aplaud在LoRA基础上改进，将适配过程分离为冻结的共享低秩基与紧凑的用户专属修正矩阵，并引入秩一残差以实现更精细个性化。为进一步降低每用户参数开销并缓解过拟合，修正矩阵可进一步分解为更低秩形式。实验表明，Aplaud在跨用户场景中实现了高效、可扩展的个性化，在泛化性能与推理效率上均优于当前最先进的基于LoRA的个性化LLM方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。