Papers › GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs

27 Aug 2024arXiv:2408.15300archive 2025-07-28

Maxim Zhelnin, Viktor Moskvoretskii, Egor Shvetsov, Egor Venediktov, Mariya Krylova, Aleksandr Zuev, Evgeny Burnaev

Parameter Efficient Fine-Tuning (PEFT) methods have gained popularity and democratized the usage of Large Language Models (LLMs). Recent studies have shown that a small subset of weights significantly impacts performance. Based on this observation, we introduce a novel PEFT method, called Gaussian noise Injected Fine Tuning of Salient Weights (GIFT-SW). Our method updates only salient columns, while injecting Gaussian noise into non-salient ones. To identify these columns, we developeda generalized sensitivity metric that extends and unifies metrics from previous studies. Experiments with LLaMA models demonstrate that GIFT-SW outperforms full fine-tuning and modern PEFT methods under the same computational budget. Moreover, GIFT-SW offers practical advantages to recover performance of models subjected to mixed-precision quantization with keeping salient weights in full precision.

PaperPDFCodeCode Syntology ran

In Syntology 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="2408.15300")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 2 samples from 1 repository, 0 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

On-Point-RND/GIFT_SW officialmentioned on GitHubpytorchApache-2.0 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

5 samples harvested; 3 ran; 2 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
2unverified

Licence: 3 of the 5 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 On-Point-RND/GIFT_SW. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

check_if_peft_model On-Point-RND/GIFT_SW/src/peft/helpers.py official repository unverified Apache-2.0 (permissive) · 6a1220317ec3675f · report
is_torch_tpu_available On-Point-RND/GIFT_SW/src/peft/import_utils.py official repository unverified Apache-2.0 (permissive) · a3daaf3e5bdfc709 · report
b2mb identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · 32380a050ca033d4 · report
get_closest_label identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · bdad3d08a6241ede · report
levenshtein_distance identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · d267d33e45b87bcd · report

Tasks

Quantizationparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
parameter-efficient fine-tuning BoolQ LLaMA2-7b Accuracy (% ) 82.63 #2 of 4 Archive leaderboard report
parameter-efficient fine-tuning HellaSwag LLaMA2-7b Accuracy (% ) 76.68 #1 of 3 Archive leaderboard report
parameter-efficient fine-tuning WinoGrande LLaMA2-7b Accuracy (% ) 70.80 #1 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LLaMA

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