Few-Shot Text Classification
8개 벤치마크 · 논문 106편 · 이 태스크의 논문 보기 →
Benchmarks
RAFT
Average on NLP datasets
Amazon Counterfeit
ODIC 10-way (10-shot)
ODIC 10-way (5-shot)
ODIC 5-way (10-shot)
ODIC 5-way (5-shot)
SST-5
Most implemented
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
Induction Networks for Few-Shot Text Classification
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
Papers
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 Answering