Papers › Composing Parameter-Efficient Modules with Arithmetic Operations

Composing Parameter-Efficient Modules with Arithmetic Operations

26 Jun 2023arXiv:2306.14870archive 2025-07-28

Jinghan Zhang, Shiqi Chen, Junteng Liu, Junxian He

As an efficient alternative to conventional full finetuning, parameter-efficient finetuning (PEFT) is becoming the prevailing method to adapt pretrained language models. In PEFT, a lightweight module is learned on each dataset while the underlying pretrained language model remains unchanged, resulting in multiple compact modules representing diverse skills when applied to various domains and tasks. In this paper, we propose to compose these parameter-efficient modules through linear arithmetic operations in the weight space, thereby integrating different module capabilities. Specifically, we first define addition and negation operators for the module, and then further compose these two basic operators to perform flexible arithmetic. Our approach requires no additional training and enables highly flexible module composition. We apply different arithmetic operations to compose the parameter-efficient modules for (1) distribution generalization, (2) multi-tasking, (3) unlearning, and (4) domain transfer. Additionally, we extend our approach to detoxify Alpaca-LoRA, the latest instruction-tuned large language model based on LLaMA. Empirical results demonstrate that our approach produces new and effective parameter-efficient modules that significantly outperform existing ones across all settings.

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 10 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 2 repositories, 5 ran (4 with no instrument failure; 1 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 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 5 samples that ran has no recorded date.

hkust-nlp/pem_composition officialmentioned in papermentioned on GitHubjaxSyntology: 3 samples, 0 ran · 3 unverified report
sjtu-lit/pem_composition officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 7 samples, 5 ran (1 instrument-failed) · 2 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

10 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 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
1ran · our draft was wrong
3ran
5unverified

Licence: 4 of the 10 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 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.

hkust-nlp/pem_composition official repository 3 samples, 0 ran · 3 unverified
adjust_tensors_for_parallel src/transformers/adapters/composition.py unverified Apache-2.0 (permissive) · b3615647974036c4 · report
parse_composition src/transformers/adapters/composition.py unverified Apache-2.0 (permissive) · fd2a1edfdefc5de3 · report
parse_heads_from_composition src/transformers/adapters/composition.py unverified Apache-2.0 (permissive) · ae8bbe37a1f80e76 · report
sjtu-lit/pem_composition official repository 7 samples, 5 ran (1 instrument-failed) · 2 unverified
adjust_length_to_model in 6 papers exps/composition_for_unlearning/gpt2_scale.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 440751480098ee7d · report fixture: signature length:int/0/int, max_sequence_length:int/0/int · returned int · level recorded, date not recorded
compute_pairwise_coefficient_sets merge.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 2c77d7dc5a31d431 · report fixture: signature step:float/0/float · returned list · level recorded 2026-09-26
find_incomplete_sentence AlpacaLoRAcomposition/detoxify_api.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · ba7e81c71b1fb5f1 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
load_input_text exps/composition_for_unlearning/run_prediction.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0ca28293fa42b301 · report fixture: signature input_obj:str/0/str · returned list · level recorded 2026-09-25
load_input_text AlpacaLoRAcomposition/detoxify_api.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 42dd792cf7755f82 · report fixture: signature input_obj:str/0/str · returned list · level recorded 2026-09-26
adapter_negation exps/composition_for_unlearning/gpt2_scale.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 950ec6a2194fb76d · report
adjust_tensors_for_parallel src/transformers/adapters/composition.py unverified Apache-2.0 (permissive) · f8ef77acae8f9f42 · report

Tasks

Language ModelingLanguage ModellingLarge Language ModelNegation

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