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

arXiv: https://arxiv.org/abs/2605.11857 · HTML: https://mlsanity.com/paper/2605.11857/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 27 of 27)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Towards Building the Federated GPT: Federated Instruction Tuning](https://mlsanity.com/paper/2305.05644/) (2023)
- [Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data](https://mlsanity.com/paper/2010.03622/) (2020)
- [FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations](https://mlsanity.com/paper/2409.05976/) (2024)
- [Understanding Gradient Clipping in Private SGD: A Geometric Perspective](https://mlsanity.com/paper/2006.15429/) (2020)
- [Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models](https://mlsanity.com/paper/2401.06432/) (2024)
- [Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources](https://mlsanity.com/paper/2402.11505/) (2024)
- [LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement](https://mlsanity.com/paper/2411.14961/) (2024)
- [Efficient Decentralized Deep Learning by Dynamic Model Averaging](https://mlsanity.com/paper/1807.03210/) (2018)
- [FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models](https://mlsanity.com/paper/2310.01467/) (2023)
- [Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients](https://mlsanity.com/paper/2410.22815/) (2024)
- [An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift](https://mlsanity.com/paper/2202.12123/) (2022)
- [Ground-Truthing AI Energy Consumption: Validating CodeCarbon Against External Measurements](https://mlsanity.com/paper/2509.22092/) (2025)
- [Little is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning](https://mlsanity.com/paper/2310.05696/) (2023)
- [Communication-Efficient Distributed Online Learning with Kernels](https://mlsanity.com/paper/1911.12899/) (2019)
- [Heterogeneous Federated Fine-Tuning with Parallel One-Rank Adaptation](https://mlsanity.com/paper/2602.16936/) (2026)
- [Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models](https://mlsanity.com/paper/2410.01948/) (2024)
- [Stabilized Fine-Tuning with LoRA in Federated Learning: Mitigating the Side Effect of Client Size and Rank via the Scaling Factor](https://mlsanity.com/paper/2603.08058/) (2026)

## Abstract (arXiv)

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.