On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View

2025/08/22 by Guo, Tao, Wang, Junxiao, Huo, Fushuo +4
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2508.16261

Abstract

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.

Citations

• Federated Learning in Practice: Reflections and Projections
• FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
• FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
• FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model
• FedPFT: Federated Proxy Fine-Tuning of Foundation Models
• DoRA: Weight-Decomposed Low-Rank Adaptation
• OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
• Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models
• Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning
• FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
• Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Fine-Tuning Language Models with Just Forward Passes
• Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models
• Offsite-Tuning: Transfer Learning without Full Model
• Affective Coherence Monitoring for Transformer-Based Language Models
• FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning
• Proof-of-Learning is Currently More Broken Than You Think
• Black-box Prompt Learning for Pre-trained Language Models
• Black-Box Tuning for Language-Model-as-a-Service
• The Power of Scale for Parameter-Efficient Prompt Tuning
• On the effect of dropping layers of pre-trained transformer models
• Prefix-Tuning: Optimizing Continuous Prompts for Generation
• Prefix-Tuning: Optimizing Continuous Prompts for Generation

Related

• Federated Large Language Models: Current Progress and Future Directions
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions
• A Survey on Federated Fine-tuning of Large Language Models
• FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
• FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices