qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs

• URL: http://arxiv.org/abs/2512.11366v1
• Date: Fri, 12 Dec 2025 08:27:34 GMT
• Title: qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs
• Authors: Shreya Shukla, Aditya Sriram, Milinda Kuppur Narayanaswamy, Hiteshi Jain,
• Abstract summary: We propose qa-FLoRA, a novel query-adaptive data-and-training-free method for LoRA fusion.<n>We show that qa-FLoRA outperforms static fusion by 5% with LLaMA-2 and 6% with LLaMA-3, and the training-free baselines by 7% with LLaMA-2 and 10% with LLaMA-3.
• Score: 1.4699455652461726
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The deployment of large language models for specialized tasks often requires domain-specific parameter-efficient finetuning through Low-Rank Adaptation (LoRA) modules. However, effectively fusing these adapters to handle complex, multi-domain composite queries remains a critical challenge. Existing LoRA fusion approaches either use static weights, which assign equal relevance to each participating LoRA, or require data-intensive supervised training for every possible LoRA combination to obtain respective optimal fusion weights. We propose qa-FLoRA, a novel query-adaptive data-and-training-free method for LoRA fusion that dynamically computes layer-level fusion weights by measuring distributional divergence between the base model and respective adapters. Our approach eliminates the need for composite training data or domain-representative samples, making it readily applicable to existing adapter collections. Extensive experiments across nine multilingual composite tasks spanning mathematics, coding, and medical domains, show that qa-FLoRA outperforms static fusion by ~5% with LLaMA-2 and ~6% with LLaMA-3, and the training-free baselines by ~7% with LLaMA-2 and ~10% with LLaMA-3, while significantly closing the gap with supervised baselines. Further, layer-level analysis of our fusion weights reveals interpretable fusion patterns, demonstrating the effectiveness of our approach for robust multi-domain adaptation.

Related papers

• FediLoRA: Heterogeneous LoRA for Federated Multimodal Fine-tuning under Missing Modalities [9.507134068207597]
  FediLoRA is a framework for federated multimodal fine-tuning under heterogeneous LoRA ranks and missing modalities.<n>It achieves superior performance over competitive baselines in both global and personalized settings.
  arXiv  Detail & Related papers  (2025-09-01T10:40:13Z)
• AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation [32.46570968627392]
  Low-rank adaptation (LoRA) have demonstrated efficacy in enabling model customization with minimal parameter overhead.<n>We introduce a novel framework that enables semantic-driven LoRA retrieval and dynamic aggregation.<n>Our approach achieves significant improvement in image generation perfermance.
  arXiv  Detail & Related papers  (2025-08-04T06:36:00Z)
• FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data [60.09659670497899]
  Large language models (LLMs) have a diverse landscape of models, each excelling at different tasks.<n>This diversity drives researchers to employ multiple LLMs in practice, leaving behind valuable multi-LLM log data.<n>We argue that practical fusion must meet two essential requirements: (1) compatibility with real-world serving scenarios (e.g., local and API-based serving), and (2) flexibility to operate at different stages of the LLM pipeline to meet varied user needs.
  arXiv  Detail & Related papers  (2025-07-14T17:58:02Z)
• LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing [17.171872354057694]
  We propose the LoRA-Mixer, a modular and lightweight MoE framework that integrates LoRA experts.<n>Our core innovation lies in replacing the projection matrices of the attention module's input/output linear layers with task-specific LoRA experts.<n>LoRA-Mixer achieves significant improvements on datasets such as GSM8K, HumanEval, and MedQA.
  arXiv  Detail & Related papers  (2025-06-17T14:58:54Z)
• LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization [78.93425154518705]
  Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements.<n>This paper introduces LoRA-RITE, a novel adaptive matrix preconditioning method for LoRA optimization.
  arXiv  Detail & Related papers  (2024-10-27T22:57:12Z)
• DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models [10.179598253424103]
  Large Language Models (LLMs) have achieved robust performance across diverse tasks, but fine-tuning these models for specific domains remains resource-intensive.<n>We propose a mini-MLP module with only 5M parameters to dynamically fuse multiple LoRAs at the sentence level using top-p sampling strategies.<n>This approach reduces inference time to less than twice that of single LoRA inference by leveraging parallel computation.
  arXiv  Detail & Related papers  (2024-10-02T12:45:52Z)
• Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning [57.36978335727009]
  Low-Rank Adaptation (LoRA) offers an efficient way to fine-tune large language models (LLMs) In this paper, we propose a framework that adaptively retrieves and composes multiple LoRAs based on input prompts.
  arXiv  Detail & Related papers  (2024-06-24T05:24:41Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models [4.978361907192563]
  MeteoRA is a scalable and efficient framework that reuses multiple task-specific LoRA adapters into the base LLM. MeteoRA achieves superior performance in handling composite tasks, effectively solving ten sequential problems in a single inference pass.
  arXiv  Detail & Related papers  (2024-05-19T20:46:07Z)
• Mixture of LoRA Experts [87.50120181861362]
  This paper introduces the Mixture of LoRA Experts (MoLE) approach, which harnesses hierarchical control and unfettered branch selection. The MoLE approach achieves superior LoRA fusion performance in comparison to direct arithmetic merging.
  arXiv  Detail & Related papers  (2024-04-21T11:59:53Z)
• LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild [76.67343971195267]
  Low-Rank Adaptation (LoRA) provides an efficient solution for fine-tuning large language models (LLM) LoraRetriever is a retrieve-then-compose framework that adaptively retrieves and composes multiple LoRAs according to the input prompts. Experimental results indicate that LoraRetriever consistently outperforms the baselines.
  arXiv  Detail & Related papers  (2024-02-15T15:02:46Z)

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.