Papers Few-Shot Text Classification
“Few-Shot Text Classification” 태그가 달린 논문 106편 · 필터 해제
Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings
Balanced k-shot sampling draws exactly k labeled examples per class. We show that it induces an exact, provable degeneracy in a family of small-sample discriminant estimators. Under balanced sampling, the within-class sc…
Few-Shot Text ClassificationGeometric Filtering of LLM-Generated Samples for Few-Shot Text Classification
Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some fall in correct class regions of the embedding space while others lan…
Few-Shot Text ClassificationText Distance from Nested and Hierarchical Repetitions: A Compression-Based Perspective
We present a new method for structural sequence analysis grounded in Algorithmic Information Theory (AIT). At its core is the Ladderpath approach, which extracts nested and hierarchical relationships among repeated subst…
Few-Shot Text ClassificationBoosting Meta-Learning for Few-Shot Text Classification via Label-guided Distance Scaling
Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the la…
Few-Shot Text ClassificationStructured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured promp…
Few-Shot Text ClassificationGFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based promp…
Few-Shot Text ClassificationQuestion AnsweringTowards Robust Few-Shot Text Classification Using Transformer Architectures and Dual Loss Strategies
Few-shot text classification has important application value in low-resource environments. This paper proposes a strategy that combines adaptive fine-tuning, contrastive learning, and regularization optimization to impro…
ClassificationContrastive LearningFew-Shot Text Classificationtext-classification+1A Hybrid Model for Few-Shot Text Classification Using Transfer and Meta-Learning
With the continuous development of natural language processing (NLP) technology, text classification tasks have been widely used in multiple application fields. However, obtaining labeled data is often expensive and diff…
Few-Shot LearningFew-Shot Text ClassificationMeta-Learningtext-classification+2TARDiS : Text Augmentation for Refining Diversity and Separability
Text augmentation (TA) is a critical technique for text classification, especially in few-shot settings. This paper introduces a novel LLM-based TA method, TARDiS, to address challenges inherent in the generation and ali…
DiversityFew-Shot Text ClassificationText Augmentationtext-classification+1Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification
Text classification is a fundamental task in natural language processing, pivotal to various applications such as query optimization, data integration, and schema matching. While neural network-based models, such as CNN …
Data IntegrationFew-Shot Text ClassificationRetrievalRetrieval-augmented Generation+2Label-template based Few-Shot Text Classification with Contrastive Learning
As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional …
Contrastive LearningFew-Shot Text ClassificationMeta-Learningtext-classification+1Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks
Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes fro…
AllFew-Shot Text ClassificationMeta-Learningtext-classification+1Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt
The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels…
ClassificationFew-Shot Text ClassificationPrompt Learningtext-classification+1Manual Verbalizer Enrichment for Few-Shot Text Classification
With the continuous development of pre-trained language models, prompt-based training becomes a well-adopted paradigm that drastically improves the exploitation of models for many natural language processing tasks. Promp…
BenchmarkingClassificationDocument ClassificationFew-Shot Learning+3Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification
Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text f…
FairnessFew-Shot LearningFew-Shot Text Classificationtext-classification+1Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords incl…
Few-Shot Text ClassificationQ-LearningReinforcement Learning (RL)Style Transfer+4LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods
With the ascent of large language models (LLM), natural language processing has witnessed enhancements, such as LLM-based data augmentation. Nonetheless, prior research harbors two primary concerns: firstly, a lack of co…
Data AugmentationFew-Shot Text Classificationtext-classificationText ClassificationFPT: Feature Prompt Tuning for Few-shot Readability Assessment
Prompt-based methods have achieved promising results in most few-shot text classification tasks. However, for readability assessment tasks, traditional prompt methods lackcrucial linguistic knowledge, which has already b…
16kFew-Shot Text ClassificationLanguage ModelingLanguage Modelling+3Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown t…
Data AugmentationFew-Shot Text Classificationtext-classificationText ClassificationCrossTune: Black-Box Few-Shot Classification with Label Enhancement
Training or finetuning large-scale language models (LLMs) requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One approach is to treat thes…
Few-Shot Text ClassificationIn-Context LearningLanguage Modellingtext-classification+1