# UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models Source: [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models]() Collection index: [llms.txt]() Data updated: 2025-12-18T14:06:49.448Z Authors: Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong, Shuhao Guan, Linbo Cao, Yining Wang Published: 2025-05-26T15:56:40.000Z ## Abstract This paper introduces Uniform Orthogonal Reinitialization Adaptation (UORA), a novel parameter-efficient fine-tuning (PEFT) approach for Large Language Models (LLMs). UORA achieves state-of-the-art performance and parameter efficiency by leveraging a low-rank approximation method to reduce the number of trainable parameters. Unlike existing methods such as LoRA and VeRA, UORA employs an interpolation-based reparametrization mechanism that selectively reinitializes rows and columns in frozen projection matrices, guided by the vector magnitude heuristic. This results in substantially fewer trainable parameters compared to LoRA and outperforms VeRA in computation and storage efficiency. Comprehensive experiments across various benchmarks demonstrate UORA's superiority in achieving competitive fine-tuning performance with negligible computational overhead. We demonstrate its performance on GLUE and E2E benchmarks and its effectiveness in instruction-tuning large language models and image classification models. Our contributions establish a new paradigm for scalable and resource-efficient fine-tuning of LLMs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()