Text Classification

Boosting toxicity classification robustness, this paper introduces a novel bi-level optimization framework integrating crowdsourced soft-labels and GroupDRO to enhance resistance against out-of-distri…

SPARTEX achieves memory-efficient extreme multi-label classification by integrating dynamic sparse training with an auxiliary loss function, enabling end-to-end training with millions of labels on com…

New criterion maximizes remaining discrepancy after rationale removal, treating spurious features as noise, improving rationale extraction.

Researchers developed a novel continual learning method achieving state-of-the-art performance by aligning data representations across tasks using pre-trained tokens, eliminating the need for experien…

Boost language model performance across domains with ‘Concentration’: a new prompt optimization objective that prioritizes stable, deep-layer attention.