{"ID":2889727,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20999","arxiv_id":"2507.20999","title":"LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning","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.","short_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 approache...","url_abs":"https://arxiv.org/abs/2507.20999","url_pdf":"https://arxiv.org/pdf/2507.20999v3","authors":"[\"Yining Huang\",\"Bin Li\",\"Keke Tang\",\"Meilian Chen\"]","published":"2025-07-28T17:11:26Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"LoRA\"]","has_code":false}