HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization

• URL: http://arxiv.org/abs/2510.12266v1
• Date: Tue, 14 Oct 2025 08:19:13 GMT
• Title: HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization
• Authors: Ziyi Han, Huanyu Wang, Zeyu Zhang, Xiangxiang Dai, Xutong Liu, John C. S. Lui,
• Abstract summary: Low-Rank Adaptation (LoRA) has emerged as a widely used technique for adapting large language models to new domains.<n>Existing methods often rely on explicit task labels or additional training, which are impractical for deployment.<n>We propose textttHiLoRA, a training-free framework that performs adaptive hierarchical routing over LoRA pools.
• Score: 39.23407996213986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-Rank Adaptation (LoRA) has emerged as a widely used technique for adapting large language models (LLMs) to new domains, due to its modular design and broad availability on platforms such as HuggingFace. This availability has motivated efforts to reuse existing LoRAs for domain generalization. However, existing methods often rely on explicit task labels or additional training, which are impractical for deployment. Moreover, they typically activate a fixed number of entire LoRA modules, leading to parameter redundancy or insufficiency that degrade performance. In this paper, we propose \texttt{HiLoRA}, a training-free framework that performs adaptive hierarchical routing over LoRA pools. Drawing on structural properties of LoRA, we define rank-one components (ROCs), in which each rank parameter is regarded as an independent unit. For a given input sequence, \texttt{HiLoRA} first adaptively selects a subset of LoRAs and determines their ROC allocation based on Gaussian likelihoods at the sequence level. At the token level, it further refines routing by activating only the most informative ROCs. We further provide theoretical guarantees that \texttt{HiLoRA} selects the most relevant LoRAs with high probability. Extensive experiments show that \texttt{HiLoRA} achieves substantial improvements in domain generalization, with accuracy gains of up to {\small $55\%$} over state-of-the-art baselines, while maintaining comparable inference throughput.

Related papers

• LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules [10.00294036303927]
  We introduce LoRA-Squeeze, a simple and efficient methodology that aims to improve standard LoRA learning.<n>Our approach posits that it is better to first learn an expressive, higher-rank solution and then compress it, rather than learning a constrained, low-rank solution directly.
  arXiv  Detail & Related papers  (2026-02-11T16:19:58Z)
• DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation [26.24723718425076]
  Mixture-of-Experts (MoE) has become a prominent paradigm for scaling Large Language Models (LLMs)<n>We propose a Dynamic Rank LoRA framework named DR-LoRA, which dynamically grows expert LoRA ranks during fine-tuning based on task-specific demands.<n>Experiments on multiple benchmarks demonstrate that DR-LoRA consistently outperforms standard LoRA and static allocation strategies under the same parameter budget.
  arXiv  Detail & Related papers  (2026-01-08T10:58:51Z)
• Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes [9.4848188271008]
  Low-Rank Adaptation (LoRA) has proven effective in reducing computational costs while maintaining performance comparable to fully fine-tuned foundation models.<n>Current adaptive LoRA methods attempt to overcome this limitation by dynamically expanding or selectively allocating ranks.<n>We introduce Stable Rank-Guided Low-Rank Adaptation (SR-LoRA), a novel framework that utilizes the stable rank of pre-trained weight matrices as a natural prior for layer-wise rank allocation.
  arXiv  Detail & Related papers  (2025-06-30T23:54:23Z)
• RaSA: Rank-Sharing Low-Rank Adaptation [67.40422142257091]
  Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs)<n>We introduce Rank-Sharing Low-Rank Adaptation (RaSA), an innovative extension that enhances the expressive capacity of LoRA by leveraging partial rank sharing across layers.<n>Our theoretically grounded and empirically validated approach demonstrates that RaSA not only maintains the core advantages of LoRA but also significantly boosts performance in challenging code and math tasks.
  arXiv  Detail & Related papers  (2025-03-16T17:16:36Z)
• BeamLoRA: Beam-Constraint Low-Rank Adaptation [51.52097743781401]
  Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.<n>We propose BeamLoRA, which conceptualizes each LoRA module as a beam where each rank naturally corresponds to a potential sub-solution.
  arXiv  Detail & Related papers  (2025-02-19T10:33:22Z)
• 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)
• Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering [35.54018186415654]
  Low-Rank Adaptation (LoRA) has emerged as a popular technique for fine-tuning large language models (LLMs) to various domains. Existing methods for LoRA composition primarily focus on task-specific adaptations that require additional training. We introduce the concept of Minimal Semantic Units (MSUs), where the parameters corresponding to each rank in LoRA function as independent units. We propose the LoRA-LEGO framework, which conducts rank-wise parameter clustering by grouping MSUs from different LoRAs into $k$ clusters.
  arXiv  Detail & Related papers  (2024-09-24T15:08:41Z)
• 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)
• 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.