analiza aiqbench
Aplaud introduces a novel low-rank decomposition framework that enhances the efficiency and scalability of personalized large language models by separating shared knowledge from user-specific corrections. This approach effectively addresses data scarcity and storage constraints while outperforming existing LoRA-based methods in generalization and inference speed. The research advances the practical deployment of fine-tuned LLMs for tasks like survey response prediction with minimal parameter overhead.
Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM
arXiv:2609.04738v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI)
arXiv:2609.04738 [cs.AI]
(or arXiv:2609.04738v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.04738 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 228 cuvinte
Subiecte conexe
[AINews] not much happened today
Latent Space · 18 sept. 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity
arXiv · 2 sept. 2026
Persuasion Undermining Control: Can AI Talk its Way Out of Human Control?
LessWrong · 18 sept. 2026