SOTAVerified

Few-Shot Text Classification

Few-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances 1

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 100 papers

TitleStatusHype
Towards Robust Few-Shot Text Classification Using Transformer Architectures and Dual Loss Strategies—0
A Hybrid Model for Few-Shot Text Classification Using Transfer and Meta-Learning—0
TARDiS : Text Augmentation for Refining Diversity and Separability—0
Graph-based Retrieval Augmented Generation for Dynamic Few-shot Text Classification—0
Label-template based Few-Shot Text Classification with Contrastive Learning—0
Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the TasksCode0
Empirical Study of Mutual Reinforcement Effect and Application in Few-shot Text Classification Tasks via Prompt—0
Manual Verbalizer Enrichment for Few-Shot Text Classification—0
Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classificationCode0
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RLCode0
LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods—0
FPT: Feature Prompt Tuning for Few-shot Readability AssessmentCode0
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning—0
CrossTune: Black-Box Few-Shot Classification with Label Enhancement—0
RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language ModelsCode0
A Soft Contrastive Learning-based Prompt Model for Few-shot Sentiment Analysis—0
Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class ClassificationCode0
Label-Aware Automatic Verbalizer for Few-Shot Text Classification—0
BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions—0
TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification—0
Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance—0
Emotion-Conditioned Text Generation through Automatic Prompt Optimization—0
Evolutionary Verbalizer Search for Prompt-based Few Shot Text ClassificationCode0
MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text ClassificationCode1
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference TransformationCode0
Show:102550
← PrevPage 1 of 4Next →
All datasetsRAFTAverage on NLP datasetsAmazon CounterfeitODIC 10-way (10-shot)ODIC 10-way (5-shot)ODIC 5-way (10-shot)ODIC 5-way (5-shot)SST-5

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1T-FewAvg0.76—Unverified
2Human (crowdsourced)Avg0.74—Unverified
3GPT-3Avg0.63—Unverified
4AdaBoostAvg0.51—Unverified
5GPT-NeoAvg0.48—Unverified
6GPT-2Avg0.46—Unverified
7BART MNLI zero-shotAvg0.38—Unverified
8Plurality-classAvg0.33—Unverified
9GPT-3 zero-shotAvg0.29—Unverified
#ModelMetricClaimedVerifiedStatus
1SetFit + OCD(5)Accuracy0.65—Unverified
2SetFit + OCDAccuracy0.64—Unverified
3T-few 3BAccuracy0.63—Unverified
4SetFitAccuracy0.62—Unverified
#ModelMetricClaimedVerifiedStatus
1SetFit + OCDAccuracy0.41—Unverified
#ModelMetricClaimedVerifiedStatus
1Induction NetworksAccuracy81.64—Unverified
#ModelMetricClaimedVerifiedStatus
1Induction NetworksAccuracy78.27—Unverified
#ModelMetricClaimedVerifiedStatus
1Induction NetworksAccuracy88.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Induction NetworksAccuracy87.16—Unverified
#ModelMetricClaimedVerifiedStatus
1SetFit + OCDAccuracy0.48—Unverified