CoCoA-Mix combines cross-entropy with a confidence penalty and a scalar-weighted mixture of specialized and generalized prompts, beating prior prompt-tuning baselines on base-to-new, cross-dataset, and few-shot incremental benchmarks.
CoA-weights were optimized using SGD with the same learning rate, a momentum of 0.9, and a weight decay of 5×10 −4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
CoCoA-Mix combines cross-entropy with a confidence penalty and a scalar-weighted mixture of specialized and generalized prompts, beating prior prompt-tuning baselines on base-to-new, cross-dataset, and few-shot incremental benchmarks.