{"ID":2853292,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16282","arxiv_id":"2510.16282","title":"Instant Personalized Large Language Model Adaptation via Hypernetwork","abstract":"Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm, require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates. We introduce Profile-to-PEFT, a scalable framework that employs a hypernetwork, trained end-to-end, to map a user's encoded profile directly to a full set of adapter parameters (e.g., LoRA), eliminating per-user training at deployment. This design enables instant adaptation, generalization to unseen users, and privacy-preserving local deployment. Experimental results demonstrate that our method outperforms both prompt-based personalization and OPPU while using substantially fewer computational resources at deployment. The framework exhibits strong generalization to out-of-distribution users and maintains robustness across varying user activity levels and different embedding backbones. The proposed Profile-to-PEFT framework enables efficient, scalable, and adaptive LLM personalization suitable for large-scale applications.","short_abstract":"Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm, require training a separate adapter for each user, making them computationally expensi...","url_abs":"https://arxiv.org/abs/2510.16282","url_pdf":"https://arxiv.org/pdf/2510.16282v1","authors":"[\"Zhaoxuan Tan\",\"Zixuan Zhang\",\"Haoyang Wen\",\"Zheng Li\",\"Rongzhi Zhang\",\"Pei Chen\",\"Fengran Mo\",\"Zheyuan Liu\",\"Qingkai Zeng\",\"Qingyu Yin\",\"Meng Jiang\"]","published":"2025-10-18T00:41:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}