The value of curated, capability-balanced supervision for adapting general language models to educational tasks spanning problem solving, curriculum understanding, and instructional support is demonstrated.
Hao Liang, Qi-Han Lin, Mei-Yi Qiang et al.· 0 citations
COAL-SQL is proposed, a unified framework combining Coverage-Guided Augmentation (CGA) and Failure-Driven Learning (FDL) that achieves 64.9% execution accuracy on the BIRD development set and outperforms baselines trained at comparable scale.
Qi-Feng Cai, Xuan-Guang Pan, Hao Liang et al.· 0 citations
DataFlex-RL, an evaluation platform for comparing choices under a common GRPO recipe, is introduced, finding that changing the data policy measurably changes the training process but does not produce a reproducible improvement over uniform training.
Hao Liang, Ming-Rui Chen, Hengyi Feng et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.