Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs

• URL: http://arxiv.org/abs/2605.11857v1
• Date: Tue, 12 May 2026 09:41:40 GMT
• Title: Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
• Abstract summary: Federated fine-tuning of large language models is commonly formulated as a parameter aggregation problem.<n>We consider an alternative formulation in which collaboration is mediated through model behavior rather than parameters.<n>We present a theoretical analysis and empirical results demonstrating that this approach can match strong federated fine-tuning baselines.
• Score: 12.534172413885342
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated fine-tuning of large language models is commonly formulated as a parameter aggregation problem. However, even parameter-efficient methods require transmitting large collections of trainable weights, assume aligned architectures, and rely on white-box access to model parameters. As model sizes continue to grow and deployments become increasingly heterogeneous, these assumptions become progressively misaligned with practical constraints. We consider an alternative formulation in which collaboration is mediated through model behavior rather than parameters. Clients fine-tune local models on private data and exchange generated outputs on a shared, public prompt set. The server maps these outputs into a semantic representation space, forms a per-prompt semantic consensus, and returns pseudo-labels for further local fine-tuning. This formulation fundamentally changes the communication scaling of federated LLM fine-tuning. The amount of information exchanged depends only on the public prompt budget and the size of the communicated behaviors, independent of model size. As a consequence, the protocol naturally accommodates heterogeneous architectures and applies directly to open-ended text generation. We present a theoretical analysis and empirical results demonstrating that this approach can match strong federated fine-tuning baselines while substantially reducing communication by orders of magnitude (e.g., analytically by a factor of $1006$ for Llama3.1-405B), as well as reductions in runtime and energy consumption. These results suggest that, for generative foundation models, behavior-level consensus provides a more appropriate abstraction for federated adaptation than parameter aggregation.

Related papers

• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance.<n>We propose MoR, a federated alignment framework that combines GRPO with Mixture-of-Rewards for heterogeneousVLMs.<n>MoR consistently outperforms federated alignment baselines in generalization and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-05-05T07:02:50Z)
• Generative Data Transformation: From Mixed to Unified Data [57.84692191369066]
  textscTaesar is a emphdata-centric framework for textbftarget-textbfal textbfregeneration.<n>It encodes cross-domain context into target sequences, enabling standard models to learn intricate dependencies without complex fusion architectures.
  arXiv  Detail & Related papers  (2026-02-26T08:30:09Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-01-31T03:11:51Z)
• RefProtoFL: Communication-Efficient Federated Learning via External-Referenced Prototype Alignment [20.458428841832742]
  Federated learning (FL) enables collaborative model training without sharing raw data in edge environments.<n>We propose RefProtoFL, a communication-efficient FL framework that integrates External-Referenced Prototype Alignment.<n>We show that RefProtoFL attains higher classification accuracy than state-of-the-art prototype-based FL baselines.
  arXiv  Detail & Related papers  (2026-01-21T08:01:14Z)
• FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation [12.544628972135905]
  We introduce Federated Representation Fine-Tuning (FedReFT), a novel approach to fine-tune the client's hidden representation.<n>FedReFT applies sparse intervention layers to steer hidden representations directly, offering a lightweight and semantically rich fine-tuning alternative.<n>We evaluate FedReFT on commonsense reasoning, arithmetic reasoning, instruction-tuning, and GLUE.
  arXiv  Detail & Related papers  (2025-08-27T22:03:19Z)
• Model Assembly Learning with Heterogeneous Layer Weight Merging [57.8462476398611]
  We introduce Model Assembly Learning (MAL), a novel paradigm for model merging.<n>MAL integrates parameters from diverse models in an open-ended model zoo to enhance the base model's capabilities.
  arXiv  Detail & Related papers  (2025-03-27T16:21:53Z)
• pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning [23.43592558078981]
  Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server.<n>Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions.<n>We propose a novel generative parameter aggregation framework for personalized FL, textttpFedGPA.
  arXiv  Detail & Related papers  (2024-09-09T15:13:56Z)
• SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead [75.87007729801304]
  SpaFL: a communication-efficient FL framework is proposed to optimize sparse model structures with low computational overhead.<n>To optimize the pruning process itself, only thresholds are communicated between a server and clients instead of parameters.<n>Global thresholds are used to update model parameters by extracting aggregated parameter importance.
  arXiv  Detail & Related papers  (2024-06-01T13:10:35Z)
• FedDD: Toward Communication-efficient Federated Learning with Differential Parameter Dropout [13.056472977860976]
  Federated Learning (FL) requires frequent exchange of model parameters, which leads to long communication delay. We propose a novel framework of Federated learning scheme with Differential parameter Dropout (FedDD) FedDD consists of two key modules: dropout rate allocation and uploaded parameter selection.
  arXiv  Detail & Related papers  (2023-08-31T16:10:22Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Semantic Correspondence with Transformers [68.37049687360705]
  We propose Cost Aggregation with Transformers (CATs) to find dense correspondences between semantically similar images. We include appearance affinity modelling to disambiguate the initial correlation maps and multi-level aggregation. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies.
  arXiv  Detail & Related papers  (2021-06-04T14:39:03Z)

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.