发表机构
Kent State University; iLambda Inc.（肯特州立大学; iLambda公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Aplaud是一种面向特定用户LLM的自适应个性化低秩分解框架，通过扩展LoRA范式实现轻量可扩展的个性化，在泛化和推理效率上优于同类方法。
AI 中文摘要
本文研究利用微调后的大语言模型（LLM）进行个性化调查回复预测的问题，该任务面临独特挑战：每个用户的训练数据有限、模型存储的可扩展性，以及需利用调查问题间的共享结构。为解决这些问题，我们提出Aplaud（自适应个性化低秩与用户特定嵌套分解），这是一种用于LLM个性化的轻量且可扩展的框架。Aplaud扩展了LoRA范式，将适配部分分离为冻结的共享低秩基和紧凑的用户特定修正项，还增加了一个秩1残差以实现更精细的个性化。为进一步降低每个用户的参数成本并缓解过拟合，修正矩阵可被分解为更低秩的形式。实验结果表明，Aplaud能在用户间实现高效、可扩展的个性化，且在泛化能力和推理效率上均优于基于LoRA的最先进个性化LLM方法。
英文摘要
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.
