SEQR: Secure and Efficient QR-based LoRA Routing

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fleshman, William, Van Durme, Benjamin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909799932755968
author Fleshman, William
Van Durme, Benjamin
author_facet Fleshman, William
Van Durme, Benjamin
contents Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models, enabling large libraries of LoRAs, each for a specific task or domain. Efficiently selecting the correct LoRA adapter for a given input remains a challenge, particularly in secure environments where supervised training of routers may raise privacy concerns. Motivated by previous approaches, we formalize the goal of unsupervised LoRA routing in terms of activation norm maximization, providing a theoretical framework for analysis. We demonstrate the discriminative power of activation norms and introduce SEQR, an unsupervised LoRA routing algorithm designed to maximize efficiency while providing strict routing guarantees. SEQR provably identifies the norm-maximizing adapter with significantly greater efficiency, making it a highly scalable and effective solution for dynamic LoRA composition. We validate our results through experiments that demonstrate improved multi-task performance and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEQR: Secure and Efficient QR-based LoRA Routing
Fleshman, William
Van Durme, Benjamin
Computation and Language
Artificial Intelligence
Machine Learning
Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models, enabling large libraries of LoRAs, each for a specific task or domain. Efficiently selecting the correct LoRA adapter for a given input remains a challenge, particularly in secure environments where supervised training of routers may raise privacy concerns. Motivated by previous approaches, we formalize the goal of unsupervised LoRA routing in terms of activation norm maximization, providing a theoretical framework for analysis. We demonstrate the discriminative power of activation norms and introduce SEQR, an unsupervised LoRA routing algorithm designed to maximize efficiency while providing strict routing guarantees. SEQR provably identifies the norm-maximizing adapter with significantly greater efficiency, making it a highly scalable and effective solution for dynamic LoRA composition. We validate our results through experiments that demonstrate improved multi-task performance and efficiency.
title SEQR: Secure and Efficient QR-based LoRA Routing
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.18093