Few-Shot Text Classification

Latest papers

9 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
Oct 8, 2026Heng Li, Yong Zhang, Ning Cheng +5Few-Shot Text Classification Adaptive Knowledge Distillation
Ping An Technology (Shenzhen) Co., Ltd., China · University of Science and Technology of China
Custom Named Entity Recognition and Topic Classification for Global Health Publications
Sep 21, 2026Genis Skura, Antoine Geissbühler, Jean-Luc FalconeNamed Entity Recognition Multi-Label Classification
University of Geneva
Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks
Aug 18, 2026Matin Amoozadeh, Amin AlipourFew-Shot Text Classification Human-AI Interaction
University of Houston Houston, USA
Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification
Aug 14, 2026Benjamín Schindler, Gonzalo A. RuzFew-Shot Text Classification Text Classification
Faculty of Engineering and Sciences Universidad Adolfo Ibáñez Millennium Nucleus for Social Data Science (SODAS) Santiago, Chile · Faculty of Engineering and Sciences Universidad Adolfo Ibáñez Millennium Nucleus for Social Data Science (SODAS) Millennium Nucleus in Data Science for Plant Resilience (PhytoLearning) Santiago, Chile
AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification
Jun 24, 2026Sourav Ghosh, Yash Bhatia, Keshav Goyal +3Semantic Textual Similarity Text Classification
Samsung R&D Institute Bangalore, India · ITBHU
Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries
May 15, 2026Liqi Zhou, Jiafu LiHealthcare Clinical Triage
Large Language Models for Biomedical Article Classification
Mar 12, 2026Jakub Proboszcz, Paweł CichoszFew-Shot Text Classification Text Classification
Institute of Computer Science, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland
Boosting Meta-Learning for Few-Shot Text Classification via Label-guided Distance Scaling
Feb 28, 2026Yunlong Gao, Xinyue Liu, Yingbo Wang +2Few-Shot Text Classification Text Classification
Dalian University of Technology, Dalian, China
Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
Feb 27, 2026Jiasen Zheng, Zijun Zhou, Huajun Zhang +3Semantic Alignment Few-Shot Text Classification
Northwestern University, Evanston, USA · Independent Researcher, San Jose, USA · Syracuse University, Syracuse, USA +3

Oct 8, 2026J/K move · Enter open · S save

PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation

Heng Li, Yong Zhang, Ning Cheng, Zhigen Li+4

Ping An Technology (Shenzhen) Co., Ltd., China · University of Science and Technology of China

Few-Shot Text Classification Adaptive Knowledge Distillation Few-Shot Domain Adaptation Knowledge Distillation RL Fine-Tuning Text Classification+1

Open paper AskPDF arXiv

Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-Policy Distillation (OPD) can improve teacher-guided adaptation by supervising student-generated rollouts, while GRPO-based reinforcement learning can further refine downstream predictions. However, existing KD-to-RL pipelines typically rely on globally fixed transition schedules, ignoring that different samples may require different amounts of teacher-guided acquisition before reward-driven refinement. We propose PIVOT (Perplexity-Informed Transition Optimization), a dynamic transition framework that routes samples between OPD and GRPO according to teacher-evaluated sequence perplexity. PIVOT moves low-perplexity samples to GRPO for reward-driven refinement while keeping high-perplexity samples under OPD for continued domain knowledge acquisition. Experiments on Banking77 and HWU64 show that PIVOT consistently outperforms continued OPD and globally synchronized OPD

\rightarrow

GRPO baselines under the same number of post-warm-up student optimization steps, achieving stronger downstream performance and more stable training dynamics.