{"url":"/task/few-shot-text-classification","name":"Few-Shot Text Classification","slug":"few-shot-text-classification","description_markdown":"Few-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances [1](https://aclanthology.org/2022.emnlp-main.87)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":100,"papers_with_code":46,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/few-shot-text-classification-on-raft","slug":"few-shot-text-classification-on-raft","dataset":"RAFT","dataset_url":"/dataset/raft","rows_in_archive":9,"metrics":["Avg","ADE","B77","NIS","OSE"," Over","SOT","SRI","TAI","ToS","TEH","TC"],"first_row_in_archive_order":{"model":"T-Few","paper_title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","paper_url":"/paper/few-shot-parameter-efficient-fine-tuning-is","paper_date":"2022-05-11","arxiv_id":"2205.05638","code_links":[{"title":"kohakublueleaf/lycoris","url":"https://github.com/kohakublueleaf/lycoris"},{"title":"r-three/t-few","url":"https://github.com/r-three/t-few"}],"syntology":null}},{"leaderboard":"/sota/few-shot-text-classification-on-average-on","slug":"few-shot-text-classification-on-average-on","dataset":"Average on NLP datasets","dataset_url":null,"rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SetFit + OCD(5)","paper_title":"OCD: Learning to Overfit with Conditional Diffusion Models","paper_url":"/paper/ocd-learning-to-overfit-with-conditional","paper_date":"2022-10-02","arxiv_id":"2210.00471","code_links":[{"title":"shaharlutatipersonal/ocd","url":"https://github.com/shaharlutatipersonal/ocd"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-text-classification-on-amazon","slug":"few-shot-text-classification-on-amazon","dataset":"Amazon Counterfeit","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SetFit + OCD","paper_title":"OCD: Learning to Overfit with Conditional Diffusion Models","paper_url":"/paper/ocd-learning-to-overfit-with-conditional","paper_date":"2022-10-02","arxiv_id":"2210.00471","code_links":[{"title":"shaharlutatipersonal/ocd","url":"https://github.com/shaharlutatipersonal/ocd"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/few-shot-text-classification-on-odic-10-way","slug":"few-shot-text-classification-on-odic-10-way","dataset":"ODIC 10-way (10-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Induction Networks","paper_title":"Induction Networks for Few-Shot Text Classification","paper_url":"/paper/few-shot-text-classification-with-induction","paper_date":"2019-02-27","arxiv_id":"1902.10482","code_links":[{"title":"zhongyuchen/few-shot-text-classification","url":"https://github.com/zhongyuchen/few-shot-text-classification"},{"title":"laohur/RelationNet","url":"https://github.com/laohur/RelationNet"},{"title":"laohur/LearnToCompareText","url":"https://github.com/laohur/LearnToCompareText"},{"title":"hongshengxin/Induction_network","url":"https://github.com/hongshengxin/Induction_network"},{"title":"mhw32/prototransformer-public","url":"https://github.com/mhw32/prototransformer-public"}],"syntology":null}},{"leaderboard":"/sota/few-shot-text-classification-on-odic-10-way-5","slug":"few-shot-text-classification-on-odic-10-way-5","dataset":"ODIC 10-way (5-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Induction Networks","paper_title":"Induction Networks for Few-Shot Text Classification","paper_url":"/paper/few-shot-text-classification-with-induction","paper_date":"2019-02-27","arxiv_id":"1902.10482","code_links":[{"title":"zhongyuchen/few-shot-text-classification","url":"https://github.com/zhongyuchen/few-shot-text-classification"},{"title":"laohur/RelationNet","url":"https://github.com/laohur/RelationNet"},{"title":"laohur/LearnToCompareText","url":"https://github.com/laohur/LearnToCompareText"},{"title":"hongshengxin/Induction_network","url":"https://github.com/hongshengxin/Induction_network"},{"title":"mhw32/prototransformer-public","url":"https://github.com/mhw32/prototransformer-public"}],"syntology":null}},{"leaderboard":"/sota/few-shot-text-classification-on-odic-5-way-10","slug":"few-shot-text-classification-on-odic-5-way-10","dataset":"ODIC 5-way (10-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Induction Networks","paper_title":"Induction Networks for Few-Shot Text Classification","paper_url":"/paper/few-shot-text-classification-with-induction","paper_date":"2019-02-27","arxiv_id":"1902.10482","code_links":[{"title":"zhongyuchen/few-shot-text-classification","url":"https://github.com/zhongyuchen/few-shot-text-classification"},{"title":"laohur/RelationNet","url":"https://github.com/laohur/RelationNet"},{"title":"laohur/LearnToCompareText","url":"https://github.com/laohur/LearnToCompareText"},{"title":"hongshengxin/Induction_network","url":"https://github.com/hongshengxin/Induction_network"},{"title":"mhw32/prototransformer-public","url":"https://github.com/mhw32/prototransformer-public"}],"syntology":null}},{"leaderboard":"/sota/few-shot-text-classification-on-odic-5-way-5","slug":"few-shot-text-classification-on-odic-5-way-5","dataset":"ODIC 5-way (5-shot)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Induction Networks","paper_title":"Induction Networks for Few-Shot Text Classification","paper_url":"/paper/few-shot-text-classification-with-induction","paper_date":"2019-02-27","arxiv_id":"1902.10482","code_links":[{"title":"zhongyuchen/few-shot-text-classification","url":"https://github.com/zhongyuchen/few-shot-text-classification"},{"title":"laohur/RelationNet","url":"https://github.com/laohur/RelationNet"},{"title":"laohur/LearnToCompareText","url":"https://github.com/laohur/LearnToCompareText"},{"title":"hongshengxin/Induction_network","url":"https://github.com/hongshengxin/Induction_network"},{"title":"mhw32/prototransformer-public","url":"https://github.com/mhw32/prototransformer-public"}],"syntology":null}},{"leaderboard":"/sota/few-shot-text-classification-on-sst-5","slug":"few-shot-text-classification-on-sst-5","dataset":"SST-5","dataset_url":"/dataset/sst-5","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SetFit + OCD","paper_title":"OCD: Learning to Overfit with Conditional Diffusion Models","paper_url":"/paper/ocd-learning-to-overfit-with-conditional","paper_date":"2022-10-02","arxiv_id":"2210.00471","code_links":[{"title":"shaharlutatipersonal/ocd","url":"https://github.com/shaharlutatipersonal/ocd"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/sst","name":"SST","full_name":"Stanford Sentiment Treebank","num_papers_in_archive":2354},{"url":"/dataset/sst-5","name":"SST-5","full_name":"","num_papers_in_archive":338},{"url":"/dataset/raft","name":"RAFT","full_name":"Realworld Annotated Few-shot Tasks","num_papers_in_archive":18},{"url":"/dataset/events-classification-biotech","name":"Events classification - Biotech news","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/zero-shot-out-of-domain-detection","name":"Zero-Shot Out-of-Domain Detection"}],"parent_tasks":[{"url":"/task/text-classification","name":"Text Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":46,"tagged_in_all":100,"items":[{"url":"/paper/exploiting-cloze-questions-for-few-shot-text","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","date":"2020-01-21","arxiv_id":"2001.07676","repositories_listed":6,"syntology":null},{"url":"/paper/few-shot-text-classification-with-induction","title":"Induction Networks for Few-Shot Text Classification","date":"2019-02-27","arxiv_id":"1902.10482","repositories_listed":5,"syntology":null},{"url":"/paper/decoupling-knowledge-from-memorization","title":"Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning","date":"2022-05-29","arxiv_id":"2205.14704","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/few-shot-parameter-efficient-fine-tuning-is","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","date":"2022-05-11","arxiv_id":"2205.05638","repositories_listed":2,"syntology":null},{"url":"/paper/transprompt-towards-an-automatic-transferable","title":"TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification","date":"2021-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/knowledgeable-prompt-tuning-incorporating","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","date":"2021-08-04","arxiv_id":"2108.02035","repositories_listed":2,"syntology":null},{"url":"/paper/automatically-identifying-words-that-can","title":"Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification","date":"2020-10-26","arxiv_id":"2010.13641","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-text-classification-with","title":"Few-shot Text Classification with Distributional Signatures","date":"2019-08-16","arxiv_id":"1908.06039","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/diverse-few-shot-text-classification-with","title":"Diverse Few-Shot Text Classification with Multiple Metrics","date":"2018-05-19","arxiv_id":"1805.07513","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/improve-meta-learning-for-few-shot-text","title":"Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks","date":"2024-10-14","arxiv_id":"2410.10454","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","repositories_listed":1,"syntology":null},{"url":"/paper/hard-prompts-made-interpretable-sparse","title":"Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL","date":"2024-07-20","arxiv_id":"2407.14733","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fpt-feature-prompt-tuning-for-few-shot","title":"FPT: Feature Prompt Tuning for Few-shot Readability Assessment","date":"2024-04-03","arxiv_id":"2404.02772","repositories_listed":1,"syntology":null},{"url":"/paper/riff-learning-to-rephrase-inputs-for-few-shot","title":"RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models","date":"2024-03-04","arxiv_id":"2403.02271","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-prompt-based-self-training-with","title":"Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification","date":"2023-12-08","arxiv_id":"2312.04982","repositories_listed":1,"syntology":null},{"url":"/paper/evolutionary-verbalizer-search-for-prompt","title":"Evolutionary Verbalizer Search for Prompt-based Few Shot Text Classification","date":"2023-06-18","arxiv_id":"2306.10514","repositories_listed":1,"syntology":null},{"url":"/paper/metricprompt-prompting-model-as-a-relevance","title":"MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text Classification","date":"2023-06-15","arxiv_id":"2306.08892","repositories_listed":1,"syntology":null},{"url":"/paper/tart-improved-few-shot-text-classification","title":"TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation","date":"2023-06-03","arxiv_id":"2306.02175","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/contrastnet-a-contrastive-learning-framework","title":"ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification","date":"2023-05-16","arxiv_id":"2305.09269","repositories_listed":1,"syntology":null},{"url":"/paper/metatroll-few-shot-detection-of-state","title":"MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters","date":"2023-03-13","arxiv_id":"2303.07354","repositories_listed":1,"syntology":null},{"url":"/paper/like-a-good-nearest-neighbor-practical","title":"Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification","date":"2023-02-17","arxiv_id":"2302.08957","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-siamese-network-for-few-shot","title":"Meta-Learning Siamese Network for Few-Shot Text Classification","date":"2023-02-05","arxiv_id":"2302.03507","repositories_listed":1,"syntology":null},{"url":"/paper/protsi-prototypical-siamese-network-with-data","title":"ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation","date":"2022-11-17","arxiv_id":"2211.09855","repositories_listed":1,"syntology":null},{"url":"/paper/ocd-learning-to-overfit-with-conditional","title":"OCD: Learning to Overfit with Conditional Diffusion Models","date":"2022-10-02","arxiv_id":"2210.00471","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/efficient-few-shot-learning-without-prompts","title":"Efficient Few-Shot Learning Without Prompts","date":"2022-09-22","arxiv_id":"2209.11055","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/adaptive-meta-learner-via-gradient-similarity","title":"Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification","date":"2022-09-10","arxiv_id":"2209.04702","repositories_listed":1,"syntology":null},{"url":"/paper/pcc-paraphrasing-with-bottom-k-sampling-and","title":"PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation","date":"2022-08-17","arxiv_id":"2208.08110","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/promptda-label-guided-data-augmentation-for","title":"PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners","date":"2022-05-18","arxiv_id":"2205.09229","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unified-prompt-tuning-for-few-shot-1","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","date":"2022-05-11","arxiv_id":"2205.05313","repositories_listed":1,"syntology":null},{"url":"/paper/ascm-an-answer-space-clustered-prompting","title":"ASCM: An Answer Space Clustered Prompting Method without Answer Engineering","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}