Papers › Towards Modular LLMs by Building and Reusing a Library of LoRAs

Towards Modular LLMs by Building and Reusing a Library of LoRAs

18 May 2024arXiv:2405.11157archive 2025-07-28

Oleksiy Ostapenko, Zhan Su, Edoardo Maria Ponti, Laurent Charlin, Nicolas Le Roux, Matheus Pereira, Lucas Caccia, Alessandro Sordoni

The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for new tasks. We study how to best build a library of adapters given multi-task data and devise techniques for both zero-shot and supervised task generalization through routing in such library. We benchmark existing approaches to build this library and introduce model-based clustering, MBC, a method that groups tasks based on the similarity of their adapter parameters, indirectly optimizing for transfer across the multi-task dataset. To re-use the library, we present a novel zero-shot routing mechanism, Arrow, which enables dynamic selection of the most relevant adapters for new inputs without the need for retraining. We experiment with several LLMs, such as Phi-2 and Mistral, on a wide array of held-out tasks, verifying that MBC-based adapters and Arrow routing lead to superior generalization to new tasks. We make steps towards creating modular, adaptable LLMs that can match or outperform traditional joint training.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.11157")

Code

Syntology Ran 13 of 14 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: community (archive-listed): 14 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/mttl mentioned on GitHubpytorchMIT 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

14 samples harvested; 13 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

13ran
1unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from microsoft/mttl. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

augment_few_shot_task microsoft/mttl/mttl/datamodule/mt_seq_to_seq_module.py community (archive-listed) ran MIT (permissive) · 9607e74609d06a5c · report
augment_prompts microsoft/mttl/mttl/datamodule/mmlu_data_module.py community (archive-listed) ran MIT (permissive) · 91c46d2158999132 · report
completion_template microsoft/mttl/mttl/datamodule/humaneval_module.py community (archive-listed) ran MIT (permissive) · 90b13d358f062991 · report
completion_template microsoft/mttl/mttl/datamodule/mbpp_datamodule.py community (archive-listed) ran MIT (permissive) · 3d1190e58b358dda · report
create_config_class_from_args microsoft/mttl/mttl/arguments.py community (archive-listed) ran MIT (permissive) · 0a70817429b93f25 · report
detect_indentation microsoft/mttl/mttl/datamodule/mbpp_datamodule.py community (archive-listed) ran fingerprinted MIT (permissive) · 801642274b17ca93 · report
instruct_template microsoft/mttl/mttl/datamodule/humaneval_module.py community (archive-listed) ran MIT (permissive) · ef9fcdcd4db23c46 · report
instruct_template microsoft/mttl/mttl/datamodule/mbpp_datamodule.py community (archive-listed) ran MIT (permissive) · d549f96aaac26455 · report
is_phi2_eval_task microsoft/mttl/mttl/datamodule/mt_seq_to_seq_module.py community (archive-listed) ran MIT (permissive) · ea35b5a896e6de9d · report
maybe_filter_hf_dataset_by_key microsoft/mttl/mttl/datamodule/clip_data_module.py community (archive-listed) ran MIT (permissive) · 8df019af71f4ed70 · report
permute_options microsoft/mttl/mttl/datamodule/mmlu_data_module.py community (archive-listed) ran MIT (permissive) · 0a3ee7f35121b4ea · report
subsample_dst microsoft/mttl/mttl/datamodule/base.py community (archive-listed) ran MIT (permissive) · 6b3aac9749e83a24 · report
take_n_examples_per_task microsoft/mttl/mttl/datamodule/base.py community (archive-listed) ran MIT (permissive) · f7e24d6e9c199261 · report
augment_few_shot microsoft/mttl/mttl/datamodule/mt_seq_to_seq_module.py community (archive-listed) unverified MIT (permissive) · 6773eed2108a3c15 · report

Tasks

Language ModelingLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterBASE

1 archive method tag without a method page not shown.

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