LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning

• URL: http://arxiv.org/abs/2507.20999v3
• Date: Tue, 16 Sep 2025 07:22:09 GMT
• Title: LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
• Authors: Yining Huang, Bin Li, Keke Tang, Meilian Chen,
• Abstract summary: We propose a dual-system LoRA framework that partitions both data and parameters by System 1 or System 2 demands.<n>Specifically, we classify task data via multi-model role-playing and voting, and partition parameters based on importance scoring.<n>Experiments show that the two-stage fine-tuning strategy, SFT and RL, lowers active parameter usage while matching or surpassing SOTA PEFT baselines.
• Score: 18.452349816982835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale generative models like DeepSeek-R1 and OpenAI-O1 benefit substantially from chain-of-thought (CoT) reasoning, yet pushing their performance typically requires vast data, large model sizes, and full-parameter fine-tuning. While parameter-efficient fine-tuning (PEFT) helps reduce cost, most existing approaches primarily address domain adaptation or layer-wise allocation rather than explicitly tailoring data and parameters to different response demands. Inspired by "Thinking, Fast and Slow," which characterizes two distinct modes of thought-System 1 (fast, intuitive, often automatic) and System 2 (slower, more deliberative and analytic)-we draw an analogy that different "subregions" of an LLM's parameters might similarly specialize for tasks that demand quick, intuitive responses versus those requiring multi-step logical reasoning. Therefore, we propose LoRA-PAR, a dual-system LoRA framework that partitions both data and parameters by System 1 or System 2 demands, using fewer yet more focused parameters for each task. Specifically, we classify task data via multi-model role-playing and voting, and partition parameters based on importance scoring, then adopt a two-stage fine-tuning strategy of training System 1 tasks with supervised fine-tuning (SFT) to enhance knowledge and intuition and refine System 2 tasks with reinforcement learning (RL) to reinforce deeper logical deliberation next. Extensive experiments show that the two-stage fine-tuning strategy, SFT and RL, lowers active parameter usage while matching or surpassing SOTA PEFT baselines.

Related papers

• Relatron: Automating Relational Machine Learning over Relational Databases [50.94254514286021]
  We present a study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks.<n>Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and accuracy is an unreliable guide for choice architecture.
  arXiv  Detail & Related papers  (2026-02-26T02:45:22Z)
• MARS: Optimizing Dual-System Deep Research via Multi-Agent Reinforcement Learning [82.14973479594367]
  Large Language Models (LLMs) for complex reasoning tasks require innovative approaches that bridge intuitive and deliberate cognitive processes.<n>This paper introduces a Multi-Agent System for Deep ReSearch (MARS) enabling seamless integration of System 1's fast, intuitive thinking with System 2's deliberate reasoning.
  arXiv  Detail & Related papers  (2025-10-06T15:42:55Z)
• TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation [19.91254891769464]
  LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness.<n>Numerous studies have shown that LoRA often introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning.<n>We propose TASO, a redundancy reduction method that leverages importance information from the pretrained model's weights to mitigate LoRA redundancy.
  arXiv  Detail & Related papers  (2025-09-22T12:29:43Z)
• Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers [16.135928990655422]
  This paper introduces textttBFS-Prover-V2, a system designed to address the dual scaling problem.<n>The first is a novel multi-turn off-policy RL framework for continually improving the performance of LLM step-prover at training time.<n>The second innovation is a planner-enhanced multi-agent search architecture that scales reasoning capabilities at inference time.
  arXiv  Detail & Related papers  (2025-09-08T09:54:18Z)
• SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling [16.742839354514512]
  We introduce SkipGPT, a dynamic layer pruning framework to optimize large language models.<n>We show that SkipGPT reduces over 40% of model parameters while matching or exceeding the performance of the original dense model.
  arXiv  Detail & Related papers  (2025-06-04T17:26:31Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning [0.6906005491572401]
  We propose a method for allocating expert numbers based on parameter sensitivity LoRA-SMoE.<n> Experimental results demonstrate that our LoRA-SMoE approach can enhance model performance while reducing the number of trainable parameters.
  arXiv  Detail & Related papers  (2025-05-06T13:22:46Z)
• PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning [54.99373314906667]
  Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks.<n>As pre-trained models grow in complexity, fully fine-tuning them for downstream applications demands substantial computational and storage resources.<n>We propose PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models.
  arXiv  Detail & Related papers  (2025-04-22T16:41:21Z)
• Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning? [45.58422897857411]
  This work explores the use of large language models (LLMs) for hyperparameter optimization by fine-tuning a parameter-efficient version of Code Llama using LoRA.<n>Our approach achieves competitive or superior Root Mean Square Error (RMSE) while substantially reducing computational overhead.<n>Results demonstrate that LLM-based optimization not only rivals established Bayesian methods like Tree-structured Parzen Estimators (TPE) but also accelerates tuning for real-world applications requiring perceptual quality and low-latency processing.
  arXiv  Detail & Related papers  (2025-04-08T13:15:47Z)
• MSPLoRA: A Multi-Scale Pyramid Low-Rank Adaptation for Efficient Model Fine-Tuning [5.412348391086257]
  We propose MSPLoRA, which introduces Global Shared LoRA, Mid-Level Shared LoRA, and Layer-Specific LoRA to capture global patterns, mid-level features, and fine-grained information.<n> Experiments on various NLP tasks demonstrate that MSPLoRA achieves more efficient adaptation and better performance while significantly reducing the number of trainable parameters.
  arXiv  Detail & Related papers  (2025-03-27T07:01:50Z)
• Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing [53.295515505026096]
  Janus-Pro-driven Prompt Parsing is a prompt- parsing module that bridges text understanding and layout generation.<n>MIGLoRA is a parameter-efficient plug-in integrating Low-Rank Adaptation into UNet (SD1.5) and DiT (SD3) backbones.<n>The proposed method achieves state-of-the-art performance on COCO and LVIS benchmarks while maintaining parameter efficiency.
  arXiv  Detail & Related papers  (2025-03-27T00:59:14Z)
• Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
  Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.<n>Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.<n>In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
  arXiv  Detail & Related papers  (2025-02-18T03:20:50Z)
• Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting [107.4034346788744]
  Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions.<n>We propose Perceiver with Register queries (PerReg+), a novel trajectory prediction framework that introduces: (1) Dual-Level Representation Learning via Self-Distillation (SD) and Masked Reconstruction (MR), capturing global context and fine-grained details; (2) Enhanced Multimodality using register-based queries and pretraining, eliminating the need for clustering and suppression; and (3) Adaptive Prompt Tuning during fine-tuning, freezing the main architecture and optimizing a small number of prompts for efficient adaptation.
  arXiv  Detail & Related papers  (2025-01-08T20:11:09Z)
• LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models [7.926974917872204]
  LoRA-SP is a novel approach utilizing randomized half-selective parameter freezing. LoRA-SP significantly reduces computational and memory requirements without compromising model performance.
  arXiv  Detail & Related papers  (2024-02-28T06:50:10Z)
• Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning [91.5113227694443]
  We propose a novel visual. sensuous-aware fine-Tuning (SPT) scheme. SPT allocates trainable parameters to task-specific important positions. Experiments on a wide range of downstream recognition tasks show that our SPT is complementary to the existing PEFT methods.
  arXiv  Detail & Related papers  (2023-03-15T12:34:24Z)

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.