Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness

• URL: http://arxiv.org/abs/2506.13479v1
• Date: Mon, 16 Jun 2025 13:35:22 GMT
• Title: Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness
• Abstract summary: Merging or routing low-rank adapters (LoRAs) has emerged as a popular solution for enhancing large language models.<n>This paper argues that the research community should shift its focus from developing new merging or routing algorithms to understanding the conditions under which reusing LoRAs is truly effective.
• Score: 6.3575026653686315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Merging or routing low-rank adapters (LoRAs) has emerged as a popular solution for enhancing large language models, particularly when data access is restricted by regulatory or domain-specific constraints. This position paper argues that the research community should shift its focus from developing new merging or routing algorithms to understanding the conditions under which reusing LoRAs is truly effective. Through theoretical analysis and synthetic two-hop reasoning and math word-problem tasks, we examine whether reusing LoRAs enables genuine compositional generalization or merely reflects shallow pattern matching. Evaluating two data-agnostic methods--parameter averaging and dynamic adapter selection--we found that reusing LoRAs often fails to logically integrate knowledge across disjoint fine-tuning datasets, especially when such knowledge is underrepresented during pretraining. Our empirical results, supported by theoretical insights into LoRA's limited expressiveness, highlight the preconditions and constraints of reusing them for unseen tasks and cast doubt on its feasibility as a truly data-free approach. We advocate for pausing the pursuit of novel methods for recycling LoRAs and emphasize the need for rigorous mechanisms to guide future academic research in adapter-based model merging and practical system designs for practitioners.

Related papers

• The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning [65.67266333751569]
  Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.<n>We propose a self-supervised reinforcement learning framework that targets the internal reasoning process without requiring ground-truth annotations.<n>We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.
  arXiv  Detail & Related papers  (2026-06-10T10:50:06Z)
• Understanding LoRA as Knowledge Memory: An Empirical Analysis [20.53732426953178]
  This work investigates a parametric approach using Low-Rank Adaptation (LoRA) as a modular knowledge memory.<n>We bridge this gap through the first systematic empirical study mapping the design space of LoRA-based memory.<n>Our findings position LoRA as the complementary axis of memory alongside RAG and ICL, offering distinct advantages.
  arXiv  Detail & Related papers  (2026-03-01T13:28:57Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA [50.97792275353563]
  We introduce a novel framework that restructures a single Low-Rank Adaptation (LoRA) module as a decomposable Rank-1 Expert Pool.<n>Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the [Guided] token.
  arXiv  Detail & Related papers  (2026-01-30T10:54:51Z)
• Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search [32.56725829132154]
  We investigate whether explicit reasoning can enhance both interpretability and performance in relevance modeling.<n>In this work, we formulate relevance modeling in Xiaohongshu search as a reasoning task.<n>We introduce a Reinforcement Learning (RL)-based training framework to enhance the grounded reasoning capabilities of GRMs.
  arXiv  Detail & Related papers  (2025-11-30T16:31:16Z)
• Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends [64.71326476563213]
  Off-policy reinforcement learning for large language models (LLMs) is attracting growing interest.<n>We present a first-principles derivation for grouprelative REINFORCE without assuming a specific training data distribution.<n>This perspective yields two general principles for adapting REINFORCE to off-policy settings.
  arXiv  Detail & Related papers  (2025-09-29T02:34:54Z)
• Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning [53.85659415230589]
  This paper systematically reviews widely adoptedReinforcement learning techniques.<n>We present clear guidelines for selecting RL techniques tailored to specific setups.<n>We also reveal that a minimalist combination of two techniques can unlock the learning capability of critic-free policies.
  arXiv  Detail & Related papers  (2025-08-11T17:39:45Z)
• PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning [57.89188317734747]
  PrismRAG trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages.<n>It instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions.
  arXiv  Detail & Related papers  (2025-07-25T00:15:31Z)
• Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities [62.05713042908654]
  This paper provides a review of advances in Large Language Models (LLMs) alignment through the lens of inverse reinforcement learning (IRL)<n>We highlight the necessity of constructing neural reward models from human data and discuss the formal and practical implications of this paradigm shift.
  arXiv  Detail & Related papers  (2025-07-17T14:22:24Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approach [1.5498930424110338]
  Large Language Models (LLMs) offer a promising complement to statistical Causal Discovery (CD) approaches.<n> Ensuring fairness in machine learning requires understanding how sensitive attributes causally influence outcomes.<n>We propose a hybrid LLM-based framework for CD that extends a breadth-first search (BFS) strategy with active learning and dynamic scoring.
  arXiv  Detail & Related papers  (2025-06-13T21:04:03Z)
• Replay to Remember: Retaining Domain Knowledge in Streaming Language Models [0.0]
  Continual learning in large language models (LLMs) typically encounters the critical challenge of catastrophic forgetting.<n>We demonstrate a method combining LoRA and a minimal replay mechanism in a realistic streaming setting.<n>Our experiments reveal that while catastrophic forgetting naturally occurs, even minimal replay significantly stabilizes and partially restores domain-specific knowledge.
  arXiv  Detail & Related papers  (2025-04-24T17:56:22Z)
• ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation [38.64751082999587]
  Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy.<n>We propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations.<n>Our study enhances LRMs' factuality while effectively integrating robust reasoning for Retrieval-Augmented Generation (RAG)
  arXiv  Detail & Related papers  (2025-03-27T17:44:18Z)
• C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models [26.560293264523903]
  Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision.<n>We propose Continual Low-Rank Adaptation (C-LoRA), a novel extension of LoRA for continual learning.<n>C-LoRA uses a learnable routing matrix to dynamically manage parameter updates across tasks.
  arXiv  Detail & Related papers  (2025-02-25T07:35:36Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs [76.40876036912537]
  Large Language Models (LLMs) demonstrate strong few-shot adaptability without requiring fine-tuning.<n>Current Visual Foundation Models (VFMs) require explicit fine-tuning with sufficient tuning data.<n>We propose a framework, LoRA Recycle, that distills a meta-LoRA from diverse pre-tuned LoRAs with a meta-learning objective.
  arXiv  Detail & Related papers  (2024-12-03T07:25:30Z)
• LoRA Dropout as a Sparsity Regularizer for Overfitting Control [18.992276878667997]
  We propose a LoRA Dropout mechanism for the LoRA-based methods. We show that appropriate sparsity would help tighten the gap between empirical and generalization risks.
  arXiv  Detail & Related papers  (2024-04-15T09:32:12Z)
• Training Neural Networks from Scratch with Parallel Low-Rank Adapters [46.764982726136054]
  We introduce LoRA-the-Explorer (LTE), a novel bi-level optimization algorithm designed to enable parallel training of multiple low-rank heads across computing nodes. Our approach includes extensive experimentation on vision transformers using various vision datasets, demonstrating that LTE is competitive with standard pre-training.
  arXiv  Detail & Related papers  (2024-02-26T18:55:13Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)

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.