RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models

arXiv:2505.18877 · cs.LG · Submitted 2025-05-24 · Read on arXiv

cs.LG

Submitted: 2025-05-24

Updated: 2026-05-29

Code: https://github.com/zhangyilang/RefLoRA

Terminology

• Adaptation — 3× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 10 episodes

Sources

• GPT-4 Technical Report
• Evaluating Large Language Models Trained on Code
• On the Measure of Intelligence
• The Llama 3 Herd of Models
• Parameter-Efficient Transfer Learning with Diff Pruning
• Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
• Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
• SocialIQA: Commonsense Reasoning about Social Interactions
• Galactica: A Large Language Model for Science
• LLaMA: Open and Efficient Foundation Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• HellaSwag: Can a Machine Really Finish Your Sentence?

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks