analiza aiqbench
Profile-to-PEFT addresses the computational bottleneck of per-user fine-tuning by using a hypernetwork to generate adapter parameters directly from user profiles, enabling instant and scalable LLM personalization. This approach eliminates the need for deployment-time training while maintaining strong generalization to unseen users and outperforming existing prompt-based or adapter-based methods. The technique offers a practical path toward efficient, privacy-preserving personalization suitable for large-scale real-world applications.
Instant Personalized Large Language Model Adaptation via Hypernetwork
arXiv:2510.16282v2 Announce Type: replace 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.
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.
Computation and Language (cs.CL)
arXiv:2510.16282 [cs.CL]
(or arXiv:2510.16282v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2510.16282 Focus to learn more arXiv-issued DOI via DataCite
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 · 238 cuvinte
Subiecte conexe
LoRA-generating hypernetworks for efficient on-device LLM generative personalization
arXiv · 22 sept. 2026
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
arXiv · 22 iul. 2026
Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models
arXiv · 6 iun. 2026
HyperZip: Efficient Data Compression through Personalized Diffusion LLMs with Hypernetworks
arXiv · 30 sept. 2026