Browse State-of-the-Art › Few-Shot Text Classification
Few-Shot Text Classification
46 papers with code · 8 benchmarks · 4 datasets archive 2025-07-28
Few-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances 1
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): RAFT (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 100 · with a code link: 46 · where Syntology ran a sample: 11 (4 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (11 of 100 tagged: 4 with a run with no instrument failure, 7 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 100 of 100, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
21 Jan 2020 6 repositories listedSome NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e. g., Radford et al., 2019).
-
27 Feb 2019 5 repositories listedTherefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
-
29 May 2022 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.
-
11 May 2022 2 repositories listedICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
-
1 Nov 2021 2 repositories listedBased on continuous prompt embeddings, we propose TransPrompt, a transferable prompting framework for few-shot learning across similar tasks.
-
4 Aug 2021 2 repositories listedTuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification.
-
26 Oct 2020 2 repositories listedA recent approach for few-shot text classification is to convert textual inputs to cloze questions that contain some form of task description, process them with a pretrained language model and map the predicted words to…
-
16 Aug 2019 2 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)In this paper, we explore meta-learning for few-shot text classification.
-
19 May 2018 2 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)We study few-shot learning in natural language domains.
-
14 Oct 2024 1 repository listedMeta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance.
-
30 Sep 2024 1 repository listedFew-shot learning benchmarks are critical for evaluating modern NLP techniques.
-
20 Jul 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses.
-
3 Apr 2024 1 repository listedOur proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks.
-
4 Mar 2024 1 repository listedPre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks.
-
8 Dec 2023 1 repository listedRecently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task.
-
18 Jun 2023 1 repository listedIn this paper, we focus on automatically constructing the optimal verbalizer and propose a novel evolutionary verbalizer search (EVS) algorithm, to improve prompt-based tuning with the high-performance verbalizer.
-
15 Jun 2023 1 repository listedDespite the promising prospects, the performance of prompting model largely depends on the design of prompt template and verbalizer.
-
3 Jun 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples)Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance.
-
16 May 2023 1 repository listedFew-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes.
-
13 Mar 2023 1 repository listedState-sponsored trolls are the main actors of influence campaigns on social media and automatic troll detection is important to combat misinformation at scale.
-
17 Feb 2023 1 repository listedFew-shot text classification systems have impressive capabilities but are infeasible to deploy and use reliably due to their dependence on prompting and billion-parameter language models.
-
5 Feb 2023 1 repository listedFew-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO).
-
17 Nov 2022 1 repository listedSubjective answer evaluation is a time-consuming and tedious task, and the quality of the evaluation is heavily influenced by a variety of subjective personal characteristics.
-
2 Oct 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y.
-
22 Sep 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)This simple framework requires no prompts or verbalizers, and achieves high accuracy with orders of magnitude less parameters than existing techniques.
-
10 Sep 2022 1 repository listedTo address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task.
-
17 Aug 2022 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)This paper presents PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation, a novel CDA framework via paraphrasing, which exploits the textual paraphrase similarity as the…
-
18 May 2022 1 repository listedExtensive experiment results on few-shot text classification tasks demonstrate the superior performance of the proposed framework by effectively leveraging label semantics and data augmentation for natural language…
-
11 May 2022 1 repository listedPrompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts.
-
1 May 2022 1 repository listedWe also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models.
-
14 Apr 2022 1 repository listed
-
13 Apr 2022 1 repository listed
-
28 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
27 Jan 2022 1 repository listed
-
16 Oct 2021 1 repository listed
-
28 Sep 2021 1 repository listed
-
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection27 Aug 2021 1 repository listed
-
9 Aug 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
1 Aug 2021 1 repository listed
-
1 Aug 2021 1 repository listed
-
26 Jul 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples) · 2 pointer-only (licence)
-
24 Apr 2021 1 repository listed
-
1 Apr 2021 1 repository listed
-
12 Mar 2021 1 repository listed Syntology official: harvested, nothing ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
28 Jan 2021 1 repository listed
-
5 Apr 2018 1 repository listed
-
Towards Robust Few-Shot Text Classification Using Transformer Architectures and Dual Loss Strategies9 May 2025 0 repositories listed
-
A Hybrid Model for Few-Shot Text Classification Using Transfer and Meta-Learning13 Feb 2025 0 repositories listed
-
Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification6 Jan 2025 0 repositories listed
-
TARDiS : Text Augmentation for Refining Diversity and Separability6 Jan 2025 0 repositories listed
-
Label-template based Few-Shot Text Classification with Contrastive Learning13 Dec 2024 0 repositories listed
-
Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt13 Oct 2024 0 repositories listed
-
Manual Verbalizer Enrichment for Few-Shot Text Classification8 Oct 2024 0 repositories listed
-
LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods29 Jun 2024 0 repositories listed
-
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning30 Mar 2024 0 repositories listed
-
CrossTune: Black-Box Few-Shot Classification with Label Enhancement19 Mar 2024 0 repositories listed
-
A Soft Contrastive Learning-based Prompt Model for Few-shot Sentiment Analysis16 Dec 2023 0 repositories listed
-
Label-Aware Automatic Verbalizer for Few-Shot Text Classification19 Oct 2023 0 repositories listed
-
BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions9 Oct 2023 0 repositories listed
-
TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification29 Aug 2023 0 repositories listed
-
Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance28 Aug 2023 0 repositories listed
-
Emotion-Conditioned Text Generation through Automatic Prompt Optimization9 Aug 2023 0 repositories listed
-
Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation23 May 2023 0 repositories listed
-
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks22 May 2023 0 repositories listed
-
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models2 May 2023 0 repositories listed
-
Boosting Few-Shot Text Classification via Distribution Estimation26 Mar 2023 0 repositories listed
-
Mask-guided BERT for Few Shot Text Classification21 Feb 2023 0 repositories listed
-
Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration5 Dec 2022 0 repositories listed
-
Understanding BLOOM: An empirical study on diverse NLP tasks27 Nov 2022 0 repositories listed
-
Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering16 Nov 2022 0 repositories listed
-
STPrompt: Semantic-guided and Task-driven prompts for Effective Few-shot Classification29 Oct 2022 0 repositories listed
-
Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification23 Oct 2022 0 repositories listed
-
Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks22 Oct 2022 0 repositories listed
-
MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification1 Oct 2022 0 repositories listed
-
Sentence-aware Adversarial Meta-Learning for Few-Shot Text Classification1 Oct 2022 0 repositories listed
-
Visual Prompt Tuning for Few-Shot Text Classification1 Oct 2022 0 repositories listed
-
Few-shot Text Classification with Dual Contrastive Consistency29 Sep 2022 0 repositories listed
-
LEA: Meta Knowledge-Driven Self-Attentive Document Embedding for Few-Shot Text Classification1 Jul 2022 0 repositories listed
-
EICO: Improving Few-Shot Text Classification via Explicit and Implicit Consistency Regularization1 May 2022 0 repositories listed
-
MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification11 Apr 2022 0 repositories listed
-
LST: Lexicon-Guided Self-Training for Few-Shot Text Classification5 Feb 2022 0 repositories listed
-
Label-guided Data Augmentation for Prompt-based Few Shot Learners16 Jan 2022 0 repositories listed
-
ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification16 Dec 2021 0 repositories listed
-
Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification17 Nov 2021 0 repositories listed
-
A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification16 Nov 2021 0 repositories listed
-
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER16 Nov 2021 0 repositories listed
-
Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification16 Nov 2021 0 repositories listed
-
Few-Shot Learning with Siamese Networks and Label Tuning16 Oct 2021 0 repositories listed
-
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification17 Aug 2021 0 repositories listed
-
Variance-reduced First-order Meta-learning for Natural Language Processing Tasks1 Jun 2021 0 repositories listed
-
Effective Few-Shot Classification with Transfer Learning1 Dec 2020 0 repositories listed
-
Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network1 Dec 2020 0 repositories listed
-
Uncertainty-aware Self-training for Few-shot Text Classification1 Dec 2020 0 repositories listed
-
When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications24 May 2020 0 repositories listed
-
Dynamic Memory Induction Networks for Few-Shot Text Classification12 May 2020 0 repositories listed
-
Knowledge Guided Metric Learning for Few-Shot Text Classification4 Apr 2020 0 repositories listed
-
Hierarchical Attention Prototypical Networks for Few-Shot Text Classification1 Nov 2019 0 repositories listed
-
When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification22 Aug 2019 0 repositories listed
-
Attentive Task-Agnostic Meta-Learning for Few-Shot Text Classification1 May 2019 0 repositories listed
-
On the Importance of Attention in Meta-Learning for Few-Shot Text Classification3 Jun 2018 0 repositories listed
Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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