Pith. sign in

REVIEW 8 cited by

LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.17604 v3 pith:S7TZDDAR submitted 2024-05-27 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords lora-xslargeloramodelsparametersstoragetrainablecomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The growth of large language models underscores the need for parameter-efficient fine-tuning. Despite its popularity, LoRA encounters storage and computational challenges when deploying multiple task- or user-specific modules. To address this, we introduce LoRA-XS, a novel fine-tuning method backed by a theoretical derivation. LoRA-XS drastically reduces trainable parameters by incorporating a small, trainable weight matrix between frozen low-rank matrices derived from the Singular Value Decomposition of pre-trained weights. This design enables LoRA-XS to reduce storage requirements by over 100x in 7B models compared to LoRA. Additionally, unlike other methods, LoRA-XS imposes no lower bound on trainable parameters - it can scale from a single parameter per module to arbitrarily large values, adapting to any storage or computational constraint. Evaluations on GLUE, GSM8K, MATH, and commonsense reasoning benchmarks across different model scales reveal that LoRA-XS consistently outperforms or matches LoRA and VeRA in accuracy, offering unmatched parameter efficiency. Our ablation studies highlight the significance of singular vectors in transformer weights, establishing LoRA-XS as a powerful, storage-efficient solution for scaling and personalizing large language models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Spectral Rewiring for Exploration, Purification, and Model Merging

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Subspace-Aligned Rewiring projects RL weight updates onto the base model’s SVD basis, retaining a compact rewiring matrix that preserves reasoning and improves exploration and multi-domain merging.

  2. Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards

    cs.LG 2026-07 reject novelty 6.0 of 10

    Non-vacuous PAC-Bayes generalization bounds for billion-parameter RLVR models, obtained by a Gumbel-max reparameterization and aggressive TinyLoRA distillation/quantization, are claimed for four tasks.

  3. ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints

    cs.CV 2025-07 conditional novelty 6.0 of 10

    LoRA adapters can be initialized with a closed-form estimate derived from constraint sets linking source and target activations, improving fine-tuning speed and accuracy.

  4. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.

  5. QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models

    cs.LG 2025-08 conditional novelty 5.0 of 10

    QR-LoRA trains only scalar coefficients on a pivoted QR basis of pretrained weights, reportedly matching full fine-tuning on GLUE with 601 parameters.

  6. Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence

    cs.LG 2025-06 conditional novelty 5.0 of 10

    CorDA++ uses data-driven SVD to initialize LoRA adapters, adding per-layer covariance selection and rank allocation that reduce forgetting and speed convergence compared to LoRA, PiSSA, QLoRA, and other baselines.

  7. Taming LLMs by Scaling Learning Rates with Gradient Grouping

    cs.LG 2025-06 conditional novelty 5.0 of 10

    An optimizer wrapper that clusters per-layer momentum and scales learning rates by cluster-wise median deviations improves perplexity and accuracy across LLM and MLLM training, and lets LoRA pretraining approach full-...

  8. LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning

    cs.CV 2025-06 reject novelty 4.0 of 10

    LARGO adds per-matrix learned projection radii and SVD-based initialization to LoRA and reports improved out-of-distribution accuracy on DomainNet, ImageNet, and VQA benchmarks.

Pith tools