Hybrid and Unitary Fine-Tuning of Large Language Models: Methods and Benchmarking under Resource Constraints

• URL: http://arxiv.org/abs/2507.18076v1
• Date: Thu, 24 Jul 2025 04:00:02 GMT
• Title: Hybrid and Unitary Fine-Tuning of Large Language Models: Methods and Benchmarking under Resource Constraints
• Authors: Haomin Qi, Zihan Dai, Chengbo Huang,
• Abstract summary: Fine-tuning large language models (LLMs) remains a computational bottleneck due to their scale and memory demands.<n>This paper presents a comprehensive evaluation of parameter-efficient fine-tuning (PEFT) techniques, including LoRA, BOFT, LoRA-GA, and uRNN.<n>By computing per-layer adaptive updates guided by gradient norms, the hybrid method achieves superior convergence efficiency and generalization across diverse tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning large language models (LLMs) remains a computational bottleneck due to their scale and memory demands. This paper presents a comprehensive evaluation of parameter-efficient fine-tuning (PEFT) techniques, including LoRA, BOFT, LoRA-GA, and uRNN, and introduces a novel hybrid strategy that dynamically integrates BOFT's orthogonal stability with LoRA-GA's gradient-aligned rapid convergence. By computing per-layer adaptive updates guided by gradient norms, the hybrid method achieves superior convergence efficiency and generalization across diverse tasks. We also explore, for the first time, the adaptation of unitary RNN (uRNN) principles to transformer-based LLMs, enhancing gradient stability through structured unitary constraints. Empirical evaluations on four benchmarks -- GLUE, GSM8K, MT-Bench, and HumanEval -- using models ranging from 7B to 405B parameters demonstrate that our hybrid method consistently outperforms individual PEFT baselines, approaching full fine-tuning accuracy while reducing resource consumption by up to 2.1 times in training time and 50 percent in memory usage. These findings establish the hybrid approach as a practical and scalable fine-tuning solution for real-world deployment of LLMs under resource constraints.

Related papers

• Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models [53.339700196282905]
  A key challenge in applying reinforcement learning to large language models (dLLMs) is the intractability of their likelihood functions.<n>We propose a memory-efficient RL algorithm that maximizes a specially constructed lower bound of the ELBO-based objective.<n> Experiments show that BGPO significantly outperforms previous RL algorithms for dLLMs in math problem solving, code generation, and planning tasks.
  arXiv  Detail & Related papers  (2025-10-13T17:47:50Z)
• Advanced Hybrid Transformer LSTM Technique with Attention and TS Mixer for Drilling Rate of Penetration Prediction [1.2432046687586285]
  Rate of Penetration (ROP) is crucial for optimizing drilling operations.<n>Traditional empirical, physics-based, and basic machine learning models often fail to capture intricate temporal and contextual relationships.<n>We propose a novel hybrid deep learning architecture integrating Long Short-Term Memory (LSTM) networks, Transformer encoders, Time-Series Mixer (TS-Mixer) blocks.
  arXiv  Detail & Related papers  (2025-08-07T09:45:56Z)
• ESSA: Evolutionary Strategies for Scalable Alignment [2.589791058467358]
  This paper introduces ESSA, a new framework that uses Evolutionary Strategies (ES) to efficiently align Large Language Models (LLMs)<n>ES is well-suited for LLM alignment due to its favorable properties, such as high parallelizability, memory efficiency, robustness to sparse rewards, and fewer data samples required for convergence.<n>Our findings establish ES as a promising and scalable alternative to gradient-based alignment, paving the way for efficient post-training of large language models.
  arXiv  Detail & Related papers  (2025-07-06T16:23:07Z)
• Taming LLMs by Scaling Learning Rates with Gradient Grouping [49.91587150497186]
  Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures.<n>This work introduces Scaling with Gradient Grouping (SGG), an gradient wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling.
  arXiv  Detail & Related papers  (2025-06-01T15:30:37Z)
• AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption [3.805501490912696]
  Federated fine-tuning has emerged as a promising approach to adapt foundation models to downstream tasks using decentralized data.<n>We propose AFLoRA, an adaptive and lightweight federated fine-tuning framework for Large Language Models.
  arXiv  Detail & Related papers  (2025-05-30T16:35:32Z)
• Flow-GRPO: Training Flow Matching Models via Online RL [75.70017261794422]
  We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models.<n>Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Equation (ODE) into an equivalent Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original inference timestep number.
  arXiv  Detail & Related papers  (2025-05-08T17:58:45Z)
• Token-Efficient RL for LLM Reasoning [0.02488650627593658]
  We propose reinforcement learning strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits.<n>Building on early policy gradient methods with baseline subtraction, we design critic-free methods that operate on a small, informative subset of output tokens.<n>We show that our methods raise accuracy on the SVAMP benchmark from 46% to over 70% and show strong performance on multi-digit multiplication.
  arXiv  Detail & Related papers  (2025-04-29T14:58:43Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We propose a new family of algorithms that uses the linear minimization oracle (LMO) to adapt to the geometry of the problem.<n>We demonstrate significant speedups on nanoGPT training using our algorithm, Scion, without any reliance on Adam.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• HeteroTune: Efficient Federated Learning for Large Heterogeneous Models [35.53420882449293]
  We propose HeteroTune, a novel federated fine-tuning paradigm for large, heterogeneous models operating under limited communication and budgets.<n>The core of our method lies in a novel architecture, DeMA, which enables flexible and efficient aggregation of heterogeneous models.<n>We provide both theoretical analysis and empirical evidence showing that HeteroTune achieves state-of-the-art performance and efficiency across diverse tasks and model architectures.
  arXiv  Detail & Related papers  (2024-11-25T09:58:51Z)
• HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization [55.972018549438964]
  Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy.<n>We propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable fine-tuning of LLMs in heterogeneous environments.<n> Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.
  arXiv  Detail & Related papers  (2024-11-10T19:59:54Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration [87.53543137162488]
  We propose an easy-to-implement online reinforcement learning (online RL) framework called textttMEX. textttMEX integrates estimation and planning components while balancing exploration exploitation automatically. It can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards.
  arXiv  Detail & Related papers  (2023-05-29T17:25:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.