# Federated Foundation Language Model Post-Training Should Focus on Open-Source Models

arXiv: https://arxiv.org/abs/2505.23593 · HTML: https://mlsanity.com/paper/2505.23593/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 63 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model](https://mlsanity.com/paper/2208.11625/) (2022)
- [Open Sesame! Universal Black Box Jailbreaking of Large Language Models](https://mlsanity.com/paper/2309.01446/) (2023)
- [Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources](https://mlsanity.com/paper/2402.11505/) (2024)
- [FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning](https://mlsanity.com/paper/2208.12268/) (2022)
- [FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model](https://mlsanity.com/paper/2406.17706/) (2024)
- [Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning](https://mlsanity.com/paper/2311.11077/) (2023)
- [A Survey on Large Language Models with some Insights on their Capabilities and Limitations](https://mlsanity.com/paper/2501.04040/) (2025)
- [Privately Fine-Tuning Large Language Models with Differential Privacy](https://mlsanity.com/paper/2210.15042/) (2022)
- [DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2309.05173/) (2023)
- [Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective](https://mlsanity.com/paper/2310.19233/) (2023)
- [A Survey on Efficient Federated Learning Methods for Foundation Model Training](https://mlsanity.com/paper/2401.04472/) (2024)
- [FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models](https://mlsanity.com/paper/2310.01467/) (2023)
- [PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2411.17453/) (2024)
- [INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation](https://mlsanity.com/paper/2306.08162/) (2023)
- [The Open Source Advantage in Large Language Models (LLMs)](https://mlsanity.com/paper/2412.12004/) (2024)
- [Secure Aggregation for Federated Learning in Flower](https://mlsanity.com/paper/2205.06117/) (2022)
- [Can Textual Gradient Work in Federated Learning?](https://mlsanity.com/paper/2502.19980/) (2025)
- [Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2412.16504/) (2024)
- [Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models](https://mlsanity.com/paper/2310.03123/) (2023)

## Abstract (arXiv)

Post-training of foundation language models has emerged as a promising research domain in federated learning (FL) with the goal to enable privacy-preserving model improvements and adaptations to user's downstream tasks. Recent advances in this area adopt centralized post-training approaches that build upon black-box foundation language models where there is no access to model weights and architecture details. Although the use of black-box models has been successful in centralized post-training, their blind replication in FL raises several concerns. Our opinion is that using black-box models in FL contradicts the core principles of federation such as data privacy and autonomy. In this paper, we critically analyze the usage of black-box models in federated post-training, and provide a detailed account of various aspects of openness and their implications for FL.