A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Trains random-forest classifiers on k-gram features from 800 paired reasoning traces to statistically detect unanswerable GSM8K problems and enable early stopping.
Yuqing Yang, Yan Ma, Pengfei Liu
Proposes a progressive weak-to-strong reasoning framework where a strong model refines its own training data without human or advanced model input, significantly improving reasoning on GSM8K and MATH.