Residual skill optimization creates complementary Text-to-SQL agents by training each new skill on prior ensemble failures, yielding accuracy gains on Spider2-Lite and transfer to other dialects and tasks.
Boosted prompt ensembles for large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
PENEX is a new formulation of the multi-class exponential loss for neural networks that supports first-order optimization and improves generalization in low-data regimes.
citing papers explorer
-
Residual Skill Optimization for Text-to-SQL Ensembles
Residual skill optimization creates complementary Text-to-SQL agents by training each new skill on prior ensemble failures, yielding accuracy gains on Spider2-Lite and transfer to other dialects and tasks.
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
-
PENEX: AdaBoost-Inspired Neural Network Regularization
PENEX is a new formulation of the multi-class exponential loss for neural networks that supports first-order optimization and improves generalization in low-data regimes.