Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts

• URL: http://arxiv.org/abs/2603.03535v1
• Date: Tue, 03 Mar 2026 21:44:11 GMT
• Title: Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts
• Authors: Sanae Lotfi, Lucas Caccia, Alessandro Sordoni, Jordan T. Ash, Miroslav Dudik,
• Abstract summary: Large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks.<n>Fusing independently trained models with different strengths has shown promise for multi-task learning through three main strategies.<n>We empirically evaluate their trade-offs, addressing two key questions: What are the advantages of going beyond uniform ensembling or merging? and does the flexibility of routing justify its complexity?
• Score: 56.02203242609604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While large language models (LLMs) fine-tuned with lightweight adapters achieve strong performance across diverse tasks, their performance on individual tasks depends on the fine-tuning strategy. Fusing independently trained models with different strengths has shown promise for multi-task learning through three main strategies: ensembling, which combines outputs from independent models; merging, which fuses model weights via parameter averaging; and routing, which integrates models in an input-dependent fashion. However, many design decisions in these approaches remain understudied, and the relative benefits of more sophisticated ensembling, merging and routing techniques are not fully understood. We empirically evaluate their trade-offs, addressing two key questions: What are the advantages of going beyond uniform ensembling or merging? And does the flexibility of routing justify its complexity? Our findings indicate that non-uniform ensembling and merging improve performance, but routing offers even greater gains. To mitigate the computational cost of routing, we analyze expert selection techniques, showing that clustering and greedy subset selection can maintain reasonable performance with minimal overhead. These insights advance our understanding of model fusion for multi-task learning.

Related papers

• From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation [59.27094165576015]
  We propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces.<n>By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process.<n>We introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning.
  arXiv  Detail & Related papers  (2026-01-28T09:29:40Z)
• Token-Level LLM Collaboration via FusionRoute [60.72307345997823]
  FusionRoute is a token-level multi-LLM collaboration framework.<n>It selects the most suitable expert at each decoding step and contributes a complementary logit that refines or corrects the selected expert's next-token distribution.<n>It outperforms both sequence- and token-level collaboration, model merging, and direct fine-tuning.
  arXiv  Detail & Related papers  (2026-01-08T16:53:16Z)
• CONCUR: A Framework for Continual Constrained and Unconstrained Routing [79.85419373937765]
  AI tasks differ in complexity and are best addressed with different computation strategies.<n>Most prior methods build the routing framework by training a single model across all strategies.<n>We propose CONCUR, a continual routing framework that supports both constrained and unconstrained routing.
  arXiv  Detail & Related papers  (2025-12-10T07:30:13Z)
• LLMRank: Understanding LLM Strengths for Model Routing [2.166956880697874]
  We introduce LLMRank, a prompt-aware routing framework that leverages rich, human-readable features extracted from prompts.<n>Unlike prior one-shot routers that rely solely on latent embeddings, LLMRank predicts per-model utility using a neural ranking model trained on RouterBench.<n>Our approach achieves up to 89.2% of oracle utility, while providing interpretable feature attributions that explain routing decisions.
  arXiv  Detail & Related papers  (2025-09-23T18:11:30Z)
• Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning [7.361665112773847]
  We propose a Two-Level Grouped Mixture Routing-of-Experts (TRGE) method to mitigate catastrophic forgetting.<n> TRGE dynamically expands the pre-trained CLIP model, assigning specific expert group for each task.<n>We leverage Multimodal Large Language Models (MLLMs) which own powerful multimodal comprehension capabilities to generate task descriptions and recognize the correct task identifier.
  arXiv  Detail & Related papers  (2025-08-11T08:18:22Z)
• RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness [28.437105789298244]
  RobustMerge is a training-free parameter-efficient merging method with complementary parameter adaptation to maintain direction robustness.<n>We establish a benchmark consisting of diverse multimodal tasks, on which we conduct experiments to certify the outstanding performance and generalizability of our method.
  arXiv  Detail & Related papers  (2025-02-24T13:52:05Z)
• Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [72.10987117380584]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.<n>We find existing methods discard task-specific information that, while causing conflicts, is crucial for performance.<n>Our approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.
  arXiv  Detail & Related papers  (2025-01-02T12:45:21Z)
• Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging [21.918559935122786]
  Model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. Traditional model merging methods often show significant performance gaps compared to fine-tuned models. We show that both shared and exclusive task-specific knowledge are crucial for merging performance, but directly merging exclusive knowledge hinders overall performance. We propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input.
  arXiv  Detail & Related papers  (2024-06-17T02:31:55Z)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts [64.94129594112557]
  Merging Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. We propose to merge most of the parameters while upscaling the Transformer layers to a weight-ensembling mixture of experts (MoE) module.
  arXiv  Detail & Related papers  (2024-02-01T08:58:57Z)

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.