class imbalance

2 items

RESEARCHarXiv CS.CL·4/22/2026

Model-Agnostic Meta Learning for Class Imbalance Adaptation

This paper introduces Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses class imbalance and data difficulty in NLP tasks. HAMR employs bi-level optimizations and a neighborhood-aware resampling mechanism to prioritize genuinely challenging samples and minority classes, showing substantial improvements on diverse imbalanced datasets.

Meta-Learning deep learning machine learning Natural Language Processing

RESEARCHarXiv CS.CL·4/10/2026

CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Data

CAMO é uma nova técnica de ensemble otimizada para dados desbalanceados, que impulsiona classes minoritárias e melhora o desempenho geral. Avaliada em benchmarks com diferentes modelos de linguagem, CAMO consistentemente atinge a maior pontuação F1 macro, estabelecendo um novo padrão.

language models ensemble methods F1-score class imbalance