Few-Shot Text Classification

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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 46 papers with code (100 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
  21 Jan 2020 6 repositories listed
  Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e.
• Induction Networks for Few-Shot Text Classification
  27 Feb 2019 5 repositories listed
  Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
• Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
  29 May 2022 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
  11 May 2022 2 repositories listed
  ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
• TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification
  1 Nov 2021 2 repositories listed
  Based on continuous prompt embeddings, we propose TransPrompt, a transferable prompting framework for few-shot learning across similar tasks.
• Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
  4 Aug 2021 2 repositories listed
  Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification.
• Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification
  26 Oct 2020 2 repositories listed
  A 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…
• Few-shot Text Classification with Distributional Signatures
  16 Aug 2019 2 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  In this paper, we explore meta-learning for few-shot text classification.
• Diverse Few-Shot Text Classification with Multiple Metrics
  19 May 2018 2 repositories listed Syntology ran 5 of 5 samples · 0 unverified
  We study few-shot learning in natural language domains.
• Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks
  14 Oct 2024 1 repository listed
  Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance.
• Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification
  30 Sep 2024 1 repository listed
  Few-shot learning benchmarks are critical for evaluating modern NLP techniques.
• Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
  20 Jul 2024 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses.
• FPT: Feature Prompt Tuning for Few-shot Readability Assessment
  3 Apr 2024 1 repository listed
  Our proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks.
• RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models
  4 Mar 2024 1 repository listed
  Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks.
• Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification
  8 Dec 2023 1 repository listed
  Recently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task.
• Evolutionary Verbalizer Search for Prompt-based Few Shot Text Classification
  18 Jun 2023 1 repository listed
  In 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.
• MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text Classification
  15 Jun 2023 1 repository listed
  Despite the promising prospects, the performance of prompting model largely depends on the design of prompt template and verbalizer.
• TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation
  3 Jun 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance.
• ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification
  16 May 2023 1 repository listed
  Few-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.
• MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters
  13 Mar 2023 1 repository listed
  State-sponsored trolls are the main actors of influence campaigns on social media and automatic troll detection is important to combat misinformation at scale.
• Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification
  17 Feb 2023 1 repository listed
  Few-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.
• Meta-Learning Siamese Network for Few-Shot Text Classification
  5 Feb 2023 1 repository listed
  Few-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).
• ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation
  17 Nov 2022 1 repository listed
  Subjective 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.
• OCD: Learning to Overfit with Conditional Diffusion Models
  2 Oct 2022 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  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.
• Efficient Few-Shot Learning Without Prompts
  22 Sep 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  This simple framework requires no prompts or verbalizers, and achieves high accuracy with orders of magnitude less parameters than existing techniques.
• Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification
  10 Sep 2022 1 repository listed
  To 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.
• PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation
  17 Aug 2022 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  This paper presents \textbf{PCC}: \textbf{P}araphrasing with Bottom-k Sampling and \textbf{C}yclic Learning for \textbf{C}urriculum Data Augmentation, a novel CDA framework via paraphrasing, which exploits the textual…
• PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners
  18 May 2022 1 repository listed
  Extensive 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…
• Towards Unified Prompt Tuning for Few-shot Text Classification
  11 May 2022 1 repository listed
  Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts.
• ASCM: An Answer Space Clustered Prompting Method without Answer Engineering
  1 May 2022 1 repository listed
  We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models.

Syntology lines on 8 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. Read from the graph 2026-09-24.