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

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

7 Jun 2024arXiv:2406.04845archive 2025-07-28

Rui Ye, Rui Ge, Xinyu Zhu, Jingyi Chai, Yaxin Du, Yang Liu, Yanfeng Wang, Siheng Chen

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rui-ye/fedllm-bench officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 11 samples, 9 ran (4 instrument-failed) · 2 unverified report
brains-group/openfedllm mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
rui-ye/openfedllm mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 7 ran (3 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

19 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
7ran · our draft was wrong
8ran
3unverified

Licence: 12 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

rui-ye/fedllm-bench official repository 11 samples, 9 ran (4 instrument-failed) · 2 unverified
compress in 35 papers
census: 1 implementation from 5 papers, 1 distinct output on one shared input
compression.py ran · our draft was wrong no licence file found · pointer only · 80dde39da1ba3708 · report fixture: signature tensor:Tensor/2/float, config:QuantizationConfig/0/? · returned tuple · level recorded 2026-09-25
gaussian_noise in 9 papers federated_learning/fed_global.py ran licence not identified · pointer only · 89b2eb0c997d6cbb · report fixture: signature data_shape:tuple/1/int, fed_args:FedArgs/0/?, script_args:ScriptArgs/0/?, device:device/0/? · returned Tensor · level recorded 2026-09-24
get_clients_this_round federated_learning/fed_global.py ran licence not identified · pointer only · 2128b33c10829870 · report fixture: signature fed_args:FedArgs/0/?, round:int/0/int · returned list · level recorded 2026-09-24
get_compressed_list in 17 papers compression.py ran · our draft was wrong no licence file found · pointer only · c5824da57107fe8c · report fixture: signature module:callable/0/?, prefix:str/0/str · returned list · level recorded 2026-09-25
get_model_config in 45 papers config.py ran · our draft was wrong licence not identified · pointer only · 93e0de8955732c63 · report fixture: signature script_args:ScriptArgs/0/? · returned tuple · level recorded 2026-09-24
get_retry_time evaluation/open_ended/gen_judge_bench.py ran · honoured contract fingerprinted licence not identified · pointer only · f632fd8875ef18c9 · report fixture: signature err_info:str/0/str · returned int · level recorded 2026-09-24
get_training_args config.py ran licence not identified · pointer only · 9250c783f987def8 · report fixture: signature script_args:ScriptArgs/0/?, new_lr:float/0/float, local_step:int/0/int · returned TrainingArguments · level recorded 2026-09-24
global_aggregate federated_learning/fed_global.py ran licence not identified · pointer only · f4ab6660068cc1b9 · report fixture: signature fed_args:FedArgs/0/?, script_args:ScriptArgs/0/?, global_dict:dict/0/?, local_dict_list:list/1/dict, sample_num_list:dict/0/?, clients_this_round:list/1/int, round_idx:int/0/int, proxy_dict:dict/0/?, opt_proxy_dict:dict/0/?, auxiliary_info:tuple/1/dict · returned tuple · level recorded 2026-09-24
remove_parent_directory_name data_module.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5297d9d21f45c15a · report fixture: signature model_path:str/0/str · returned str · level recorded 2026-09-25
get_conv_template in 72 papers conversation.py unverified no licence file found · pointer only · 174d0858d8cf33ca · report
load_compress_model in 15 papers compression.py unverified licence not identified · pointer only · 5196732e9a84b6dc · report
rui-ye/openfedllm community (archive-listed) 8 samples, 7 ran (3 instrument-failed) · 1 unverified
get_auxiliary_dict federated_learning/fed_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 962adc31294b40bf · report fixture: signature fed_args:FedArgs/0/?, global_dict:dict/0/? · returned tuple · level recorded 2026-09-24
get_dataset_this_round federated_learning/split_dataset.py ran Apache-2.0 (permissive) · 9c102ddaa014f4d2 · report fixture: signature dataset:Dataset/0/?, round:int/0/int, fed_args:FedArgs/0/?, script_args:ScriptArgs/0/? · returned Dataset · level recorded 2026-09-24
get_model_config in 45 papers config.py ran · our draft was wrong Apache-2.0 (permissive) · 79b93353bd3c904e · report fixture: signature script_args:ScriptArgs/0/? · returned tuple · level recorded 2026-09-24
get_proxy_dict federated_learning/fed_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 38486baf4c608ec4 · report fixture: signature fed_args:FedArgs/0/?, global_dict:dict/0/? · returned tuple · level recorded 2026-09-24
get_training_args config.py ran Apache-2.0 (permissive) · 83d9e1534d3a0be4 · report fixture: signature script_args:ScriptArgs/0/?, new_lr:float/0/float · returned TrainingArguments · level recorded 2026-09-24
global_aggregate federated_learning/fed_global.py ran Apache-2.0 (permissive) · 8fef5b18a4b5d83b · report fixture: signature fed_args:FedArgs/0/?, global_dict:dict/0/?, local_dict_list:list/1/dict, sample_num_list:dict/0/?, clients_this_round:list/1/int, round_idx:int/0/int, proxy_dict:dict/0/?, opt_proxy_dict:dict/0/?, auxiliary_info:tuple/1/dict · returned tuple · level recorded 2026-09-24
split_dataset in 65 papers federated_learning/split_dataset.py ran Apache-2.0 (permissive) · 60c6c78eb9667d17 · report fixture: signature fed_args:FedArgs/0/?, script_args:ScriptArgs/0/?, dataset:Dataset/0/? · returned list · level recorded 2026-09-24
get_conv_template in 72 papers utils/conversation.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 506ee6d4bab01412 · report

Tasks

Federated Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections