On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) enables training models across decentralized data silos while preserving client data privacy. Recent research has explored efficient methods for post-training large language models (LLMs) within FL to address computational and communication challenges. While existing approaches often rely on access to LLMs' internal information, which is frequently restricted in real-world scenarios, an inference-only paradigm (black-box FedLLM) has emerged to address these limitations. This paper presents a comprehensive survey on federated tuning for LLMs. We propose a taxonomy categorizing existing studies along two axes: model access-based and parameter efficiency-based optimization. We classify FedLLM approaches into white-box, gray-box, and black-box techniques, highlighting representative methods within each category. We review emerging research treating LLMs as black-box inference APIs and discuss promising directions and open challenges for future research.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 44 references that are in the map. First posted on arXiv 22 Aug 2025.
Builds on
28 of 44 references.
References · 28
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
- 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
- 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
- 2023Fine-Tuning Language Models with Just Forward Passescited by 345
- 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Modelscited by 261
- 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
- 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 149
- 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 146
16 more
- 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 128
- 2020On the Effect of Dropping Layers of Pre-trained Transformer Modelscited by 118
- 2024Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Modelscited by 116
- 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 91
- 2023Offsite-Tuning: Transfer Learning without Full Modelcited by 78
- 2024FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Modelcited by 74
- 2022Black-box Prompt Learning for Pre-trained Language Modelscited by 70
- 2023Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimizationcited by 65
- 2023Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytescited by 55
- 2023Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Modelscited by 50
- 2024A Survey on Efficient Federated Learning Methods for Foundation Model Trainingcited by 29
- 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 21
- 2024FedPFT: Federated Proxy Fine-Tuning of Foundation Modelscited by 16
- 2024Federated Learning in Practice: Reflections and Projectionscited by 15
- 2022Proof-of-Learning is Currently More Broken Than You Thinkcited by 12
- 2024FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injectioncited by 8
Built on by
Not cited yet.