# FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models

arXiv: https://arxiv.org/abs/2406.04845 · HTML: https://mlsanity.com/paper/2406.04845/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 96 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 30 of 65)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (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)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)

## Built on by (most cited first, 30 of 30)

- [Federated Large Language Models: Current Progress and Future Directions](https://mlsanity.com/paper/2409.15723/) (2024)
- [Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models](https://mlsanity.com/paper/2406.10630/) (2024)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [POPri: Private Federated Learning using Preference-Optimized Synthetic Data](https://mlsanity.com/paper/2504.16438/) (2025)
- [FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2506.02961/) (2025)
- [Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2503.16585/) (2025)
- [FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Models](https://mlsanity.com/paper/2506.09638/) (2025)
- [Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning](https://mlsanity.com/paper/2410.23660/) (2024)
- [Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective](https://mlsanity.com/paper/2602.15671/) (2026)
- [Symmetric Pruning of Large Language Models](https://mlsanity.com/paper/2501.18980/) (2025)
- [FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data](https://mlsanity.com/paper/2503.05143/) (2025)
- [FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing](https://mlsanity.com/paper/2505.08325/) (2025)
- [Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models](https://mlsanity.com/paper/2409.07136/) (2024)
- [AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs](https://mlsanity.com/paper/2601.22710/) (2026)
- [Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation](https://mlsanity.com/paper/2602.15897/) (2026)
- [ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data](https://mlsanity.com/paper/2603.00516/) (2026)
- [Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security](https://mlsanity.com/paper/2406.09831/) (2024)
- [Data Quality Control in Federated Instruction-tuning of Large Language Models](https://mlsanity.com/paper/2410.11540/) (2024)
- [Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2506.06060/) (2025)
- [EmbTracker: Traceable Black-box Watermarking for Federated Language Models](https://mlsanity.com/paper/2603.12089/) (2026)
- [SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks](https://mlsanity.com/paper/2608.10144/) (2026)
- [Privacy-Preserving Offloading for Large Language Models in 6G Vehicular Networks](https://mlsanity.com/paper/2509.05320/) (2025)
- [Empowering Contrastive Federated Sequential Recommendation with LLMs](https://mlsanity.com/paper/2602.09306/) (2026)
- [Knowledge-Free Correlated Agreement for Incentivizing Federated Learning](https://mlsanity.com/paper/2605.04747/) (2026)
- [Concordia: Self-Improving Synthetic Tables for Federated LLMs](https://mlsanity.com/paper/2605.09855/) (2026)
- [Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning](https://mlsanity.com/paper/2605.13936/) (2026)
- [Silent Failures in Federated Personalization of Foundation Models](https://mlsanity.com/paper/2606.00947/) (2026)
- [Improving Federated Graph Recommendation with Semantic Guidance](https://mlsanity.com/paper/2606.15277/) (2026)
- [Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment](https://mlsanity.com/paper/2608.25114/) (2026)
- [Collaborative Personalized Preference Alignment for LLMs under Data Deficiency](https://mlsanity.com/paper/2610.05898/) (2026)

## Abstract (arXiv)

Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM). Following this training paradigm, the community has put massive efforts from diverse aspects including framework, performance, and privacy. However, an unpleasant fact is that there are currently no realistic datasets and benchmarks for FedLLM and previous works all rely on artificially constructed datasets, failing to capture properties in real-world scenarios. Addressing this, we propose FedLLM-Bench, which involves 8 training methods, 4 training datasets, and 6 evaluation metrics, to offer a comprehensive testbed for the FedLLM community. FedLLM-Bench encompasses three datasets (e.g., user-annotated multilingual dataset) for federated instruction tuning and one dataset (e.g., user-annotated preference dataset) for federated preference alignment, whose scale of client number ranges from 38 to 747. Our datasets incorporate several representative diversities: language, quality, quantity, instruction, length, embedding, and preference, capturing properties in real-world scenarios. Based on FedLLM-Bench, we conduct experiments on all datasets to benchmark existing FL methods and provide empirical insights (e.g., multilingual collaboration). We believe that our FedLLM-Bench can benefit the FedLLM community by reducing required efforts, providing a practical testbed, and promoting fair comparisons. Code and datasets are available at https://github.com/rui-ye/FedLLM-Bench.