{"slug": "aplaud-adaptive-personalized-low-rank-decomposition-for-user-specific-llm", "title": "Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM", "summary": "Researchers propose Aplaud (Adaptive Personalized Low-rank and User-specific Nested Decomposition), a lightweight framework for personalizing large language models (LLMs) to individual users, which separates adaptation into a frozen shared low-rank basis and a compact user-specific correction with a rank-one residual. In empirical tests, Aplaud outperforms state-of-the-art LoRA-based personalized LLM approaches in both generalization and inference efficiency while reducing per-user parameter cost.", "body_md": "arXiv:2609.04738v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/aplaud-adaptive-personalized-low-rank-decomposition-for-user-specific-llm", "canonical_source": "https://www.machinebrief.com/news/aplaud-adaptive-personalized-low-rank-decomposition-for-user-qx27", "published_at": "2026-09-07 04:00:00+00:00", "updated_at": "2026-09-07 04:56:36.233264+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "machine-learning"], "entities": ["Aplaud"], "alternates": {"html": "https://wpnews.pro/news/aplaud-adaptive-personalized-low-rank-decomposition-for-user-specific-llm", "markdown": "https://wpnews.pro/news/aplaud-adaptive-personalized-low-rank-decomposition-for-user-specific-llm.md", "text": "https://wpnews.pro/news/aplaud-adaptive-personalized-low-rank-decomposition-for-user-specific-llm.txt", "jsonld": "https://wpnews.pro/news/aplaud-adaptive-personalized-low-rank-decomposition-for-user-specific-llm.jsonld"}}