Papers › OTTER: Effortless Label Distribution Adaptation of Zero-shot Models

OTTER: Effortless Label Distribution Adaptation of Zero-shot Models

12 Apr 2024arXiv:2404.08461archive 2025-07-28

Changho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma, Frederic Sala

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the label distribution are not suitable in zero-shot settings, as they have mismatching requirements, such as needing access to labeled downstream task data or knowledge of the true label balance in the pretraining distribution. We sidestep these challenges and introduce a simple and lightweight approach to adjust pretrained model predictions via optimal transport. Our technique requires only an estimate of the label distribution of a downstream task. Theoretically, we characterize the improvement produced by our procedure under certain mild conditions and provide bounds on the error caused by misspecification. Empirically, we validate our method in a wide array of zero-shot image and text classification tasks, improving accuracy by 4.8% and 15.9% on average, and beating baselines like prior matching -- often by significant margins -- in 17 out of 21 datasets.

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 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 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: 6 samples from 1 repository, 6 ran (5 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 6 samples that ran have no recorded date.

sprocketlab/otter officialmentioned in papermentioned on GitHubpytorchSyntology: 6 samples, 6 ran (1 instrument-failed) · 0 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · our draft was wrong
2ran

Licence: 6 of the 6 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 sprocketlab/otter. “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.

sprocketlab/otter official repository 6 samples, 6 ran (1 instrument-failed) · 0 unverified
get_dirichlet_marginal src/label_shift_utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1cfa2c1ff434c8e4 · report fixture: signature alpha:ndarray/1/float, seed:int/0/int · returned ndarray · level recorded, date not recorded
get_pred_proba src/inference.py ran · honoured contract fingerprinted no licence file found · pointer only · 906d7af106469e1c · report fixture: signature emb:ndarray/2/float, label_encodings:ndarray/2/float, temperature:float/0/float · returned ndarray · level recorded, date not recorded
get_uniformly_resampled_indices src/label_shift_utils.py ran no licence file found · pointer only · cc97ef5fea3909c0 · report fixture: signature y:ndarray/1/int, num_labels:int/0/int, n_samples_per_class:int/0/int, seed:int/0/int · returned ndarray · level recorded 2026-09-24
get_uniformly_resampled_indices_split src/label_shift_utils.py ran no licence file found · pointer only · 9a9b5fe4892aeffb · report fixture: signature y:ndarray/1/int, num_labels:int/0/int, n_samples_per_class:int/0/int, seed:int/0/int, train_split_ratio:float/0/float · returned tuple · level recorded 2026-09-24
nlh_cost_matrix src/inference.py ran · honoured contract fingerprinted no licence file found · pointer only · 4392943c8aa127bf · report fixture: signature emb:ndarray/2/float, label_encodings:ndarray/2/float, epsilon:float/0/float · returned ndarray · level recorded, date not recorded
zs_predict src/inference.py ran · honoured contract fingerprinted no licence file found · pointer only · 9edefb19aec9bef9 · report fixture: signature emb:ndarray/2/float, label_encodings:ndarray/2/float, temperature:float/0/float · returned ndarray · level recorded, date not recorded

Tasks

ClassificationText ClassificationZero-Shot Learningtext-classification

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