# PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA

arXiv: https://arxiv.org/abs/2402.16902 · HTML: https://mlsanity.com/paper/2402.16902/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 24 Feb 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [VeRA: Vector-based Random Matrix Adaptation](https://mlsanity.com/paper/2310.11454/) (2023)
- [Lessons on Parameter Sharing across Layers in Transformers](https://mlsanity.com/paper/2104.06022/) (2021)
- [LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs](https://mlsanity.com/paper/2401.16160/) (2024)
- [Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers](https://mlsanity.com/paper/2101.00234/) (2021)
- [EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation](https://mlsanity.com/paper/2202.07959/) (2022)
- [NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services](https://mlsanity.com/paper/2307.06148/) (2023)

## Built on by (most cited first, 16 of 16)

- [Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead](https://mlsanity.com/paper/2407.00066/) (2024)
- [QSpec: Speculative Decoding with Complementary Quantization Schemes](https://mlsanity.com/paper/2410.11305/) (2024)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision](https://mlsanity.com/paper/2406.03051/) (2024)
- [Benchmarking Large Language Models on Multiple Tasks in Bioinformatics NLP with Prompting](https://mlsanity.com/paper/2503.04013/) (2025)
- [AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots](https://mlsanity.com/paper/2409.11905/) (2024)
- [MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure](https://mlsanity.com/paper/2409.15371/) (2024)
- [MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards](https://mlsanity.com/paper/2410.00938/) (2024)
- [TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning](https://mlsanity.com/paper/2503.17195/) (2025)
- [Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models](https://mlsanity.com/paper/2502.13533/) (2025)
- [Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2403.07440/) (2024)
- [Biological Sequence with Language Model Prompting: A Survey](https://mlsanity.com/paper/2503.04135/) (2025)
- [A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation](https://mlsanity.com/paper/2601.22708/) (2026)
- [Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models](https://mlsanity.com/paper/2503.03702/) (2025)
- [LoRMA: Low-Rank Multiplicative Adaptation for LLMs](https://mlsanity.com/paper/2506.07621/) (2025)
- [MoR: Mixture of Ranks for Low-Rank Adaptation Tuning](https://mlsanity.com/paper/2410.13408/) (2024)

## Abstract (arXiv)

With the rapid scaling of large language models (LLMs), serving numerous low-rank adaptations (LoRAs) concurrently has become increasingly impractical, leading to unaffordable costs and necessitating more parameter-efficient finetuning methods. In this work, we introduce Partially Rotation-enhanced Low-Rank Adaptation (PRoLoRA), an intra-layer sharing mechanism comprising four essential components: broadcast reduction, rotation enhancement, partially-sharing refinement, and rectified initialization strategy. As a superset of LoRA, PRoLoRA retains its advantages, and effectively circumvent the drawbacks of peer parameter-sharing methods with superior model capacity, practical feasibility, and broad applicability. Empirical experiments demonstrate the remarkably higher parameter efficiency of PRoLoRA in both specific parameter budget and performance target scenarios, and its scalability to larger LLMs. Notably, with one time less trainable parameters, PRoLoRA still outperforms LoRA on multiple instruction tuning datasets. Subsequently, an ablation study is conducted to validate the necessity of individual components and highlight the superiority of PRoLoRA over three potential variants. Hopefully, the conspicuously higher parameter efficiency can establish PRoLoRA as a resource-friendly alternative to LoRA.