{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","arxiv_id":"2104.14690","date":"2021-04-29","proceeding":null,"authors":["Sinong Wang","Han Fang","Madian Khabsa","Hanzi Mao","Hao Ma"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2104.14690v1","url_pdf":"https://arxiv.org/pdf/2104.14690v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"entailment-as-few-shot-learner","repo_url":"https://github.com/cactilab/hateguard","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"entailment-as-few-shot-learner","repo_url":"https://github.com/sunyilgdx/prompts4keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"entailment-as-few-shot-learner","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/efl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"subjectivity-analysis","task_name":"Subjectivity Analysis"},{"task_slug":"topic-classification","task_name":"Topic Classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":5,"of":43,"metrics":{"Accuracy":"86.4%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-qnli","task":"Natural Language Inference","dataset":"QNLI","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":16,"of":43,"metrics":{"Accuracy":"94.5%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":15,"of":90,"metrics":{"Accuracy":"90.5%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"RoBERTa-large 355M + EFL + UCA","rank_in_archive_order":22,"of":90,"metrics":{"Accuracy":"87.2%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"Neural Tree Indexers for Text Understanding","rank_in_archive_order":3,"of":98,"metrics":{"% Test Accuracy":"93.1","Parameters":"355"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"EFL (Entailment as Few-shot Learner) + RoBERTa-large","rank_in_archive_order":4,"of":98,"metrics":{"% Test Accuracy":"93.1","% Train Accuracy":"?","Parameters":"355m"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-identification-on-quora-question","task":"Paraphrase Identification","dataset":"Quora Question Pairs","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":2,"of":31,"metrics":{"F1":"89.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-boolq","task":"Question Answering","dataset":"BoolQ","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":15,"of":65,"metrics":{"Accuracy":"86.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-mrpc","task":"Semantic Textual Similarity","dataset":"MRPC","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":39,"of":45,"metrics":{"F1":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":11,"of":66,"metrics":{"Pearson Correlation":"0.918"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-cr","task":"Sentiment Analysis","dataset":"CR","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"92.5"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":5,"of":49,"metrics":{"Accuracy":"96.1"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-mpqa","task":"Sentiment Analysis","dataset":"MPQA","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"90.8"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-mr","task":"Sentiment Analysis","dataset":"MR","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":2,"of":19,"metrics":{"Accuracy":"92.5"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":9,"of":87,"metrics":{"Accuracy":"96.9"},"uses_additional_data":false},{"leaderboard":"/sota/subjectivity-analysis-on-subj","task":"Subjectivity Analysis","dataset":"SUBJ","model":"RoBERTa-large 355M + Entailment as Few-shot Learner","rank_in_archive_order":3,"of":19,"metrics":{"Accuracy":"97.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.14690","atlas_url":"https://app.syntology.ai/?focus=2104.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14690"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.14690"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.14690"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.14690\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2104.14690"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.14690\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.14690"},"call":"get_concepts_for_paper(arxiv_id=\"2104.14690\")"}],"by_repo":[{"repo":"cactilab/hateguard","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sunyilgdx/prompts4keras","kind":"listed","samples":3,"ran":1,"instrument":0,"unverified":2},{"repo":"PaddlePaddle/PaddleNLP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.03416"],"harvested_for_calls":[{"arxiv_id":"2301.03416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.03416"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.03416\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2104.14690.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2104.14690.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunyilgdx/prompts4keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/efl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cactilab/hateguard","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"unverified":2},"n_samples":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":3,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"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_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":1,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"e551df2d82036969","code_sha256_prefix":"e551df2d82036969","entry":"is_chinese","repo":"sunyilgdx/prompts4keras","repo_kind":"listed","path":"baselines/efl_classification_roberta.py","file_url":"https://github.com/sunyilgdx/prompts4keras/blob/HEAD/baselines/efl_classification_roberta.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"string:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/is-chinese","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e551df2d82036969"}},{"code_sha256":"331fd9bebe591b2f","code_sha256_prefix":"331fd9bebe591b2f","entry":"evaluate","repo":"sunyilgdx/prompts4keras","repo_kind":"listed","path":"baselines/efl_classification_bert.py","file_url":"https://github.com/sunyilgdx/prompts4keras/blob/HEAD/baselines/efl_classification_bert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/evaluate","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"331fd9bebe591b2f"}},{"code_sha256":"95f4bc09fa08c171","code_sha256_prefix":"95f4bc09fa08c171","entry":"evaluate","repo":"sunyilgdx/prompts4keras","repo_kind":"listed","path":"baselines/efl_classification_roberta.py","file_url":"https://github.com/sunyilgdx/prompts4keras/blob/HEAD/baselines/efl_classification_roberta.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/evaluate","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95f4bc09fa08c171"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dc1591b96306ab1fe09d68f3bf4c5bfcc197c917e22c88d8d55b7c5cc561b0cb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}