Papers › Entailment as Few-Shot Learner

Entailment as Few-Shot Learner

29 Apr 2021arXiv:2104.14690archive 2025-07-28

Sinong Wang, Han Fang, Madian Khabsa, Hanzi Mao, Hao Ma

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners. However, their success hinges largely on scaling model parameters to a degree that makes it challenging to train and serve. In this paper, we propose a new approach, named as EFL, that can turn small LMs into better few-shot learners. The key idea of this approach is to reformulate potential NLP task into an entailment one, and then fine-tune the model with as little as 8 examples. We further demonstrate our proposed method can be: (i) naturally combined with an unsupervised contrastive learning-based data augmentation method; (ii) easily extended to multilingual few-shot learning. A systematic evaluation on 18 standard NLP tasks demonstrates that this approach improves the various existing SOTA few-shot learning methods by 12%, and yields competitive few-shot performance with 500 times larger models, such as GPT-3.

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 3 code samples harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 3 samples from 1 repository, 1 ran (1 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

cactilab/hateguard mentioned on GitHubApache-2.0Syntology: not harvested report
sunyilgdx/prompts4keras mentioned on GitHubtfSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
PaddlePaddle/PaddleNLP paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation... (arXiv:2301.03416; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

3 samples harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

1ran · violated contract
2unverified

Licence: 0 of the 3 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 sunyilgdx/prompts4keras. “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.

sunyilgdx/prompts4keras community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
is_chinese in 6 papers baselines/efl_classification_roberta.py ran · violated contract Apache-2.0 (permissive) · e551df2d82036969 · report fixture: signature string:str/0/str · returned bool · level recorded 2026-09-22
evaluate in 514 papers baselines/efl_classification_bert.py unverified Apache-2.0 (permissive) · 331fd9bebe591b2f · report
evaluate in 514 papers baselines/efl_classification_roberta.py unverified Apache-2.0 (permissive) · 95f4bc09fa08c171 · report

Tasks

Contrastive LearningData AugmentationFew-Shot LearningLinguistic AcceptabilityNatural Language InferenceParaphrase IdentificationQuestion AnsweringSemantic Textual SimilaritySentiment AnalysisSubjectivity AnalysisTopic Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Linguistic Acceptability CoLA RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 86.4% #5 of 43 Archive leaderboard report
Natural Language Inference QNLI RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 94.5% #16 of 43 Archive leaderboard report
Natural Language Inference RTE RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 90.5% #15 of 90 Archive leaderboard report
Natural Language Inference RTE RoBERTa-large 355M + EFL + UCA Accuracy 87.2% #22 of 90 Archive leaderboard report
Natural Language Inference SNLI Neural Tree Indexers for Text Understanding % Test Accuracy 93.1 #3 of 98 Archive leaderboard report
Natural Language Inference SNLI Neural Tree Indexers for Text Understanding Parameters 355 #3 of 98 Archive leaderboard report
Natural Language Inference SNLI EFL (Entailment as Few-shot Learner) + RoBERTa-large % Test Accuracy 93.1 #4 of 98 Archive leaderboard report
Natural Language Inference SNLI EFL (Entailment as Few-shot Learner) + RoBERTa-large % Train Accuracy ? #4 of 98 Archive leaderboard report
Natural Language Inference SNLI EFL (Entailment as Few-shot Learner) + RoBERTa-large Parameters 355m #4 of 98 Archive leaderboard report
Paraphrase Identification Quora Question Pairs RoBERTa-large 355M + Entailment as Few-shot Learner F1 89.2 #2 of 31 Archive leaderboard report
Question Answering BoolQ RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 86.0 #15 of 65 Archive leaderboard report
Semantic Textual Similarity MRPC RoBERTa-large 355M + Entailment as Few-shot Learner F1 91.0 #39 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark RoBERTa-large 355M + Entailment as Few-shot Learner Pearson Correlation 0.918 #11 of 66 Archive leaderboard report
Sentiment Analysis CR RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 92.5 #3 of 9 Archive leaderboard report
Sentiment Analysis IMDb RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 96.1 #5 of 49 Archive leaderboard report
Sentiment Analysis MPQA RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 90.8 #1 of 4 Archive leaderboard report
Sentiment Analysis MR RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 92.5 #2 of 19 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 96.9 #9 of 87 Archive leaderboard report
Subjectivity Analysis SUBJ RoBERTa-large 355M + Entailment as Few-shot Learner Accuracy 97.1 #3 of 19 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

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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