Disjoint SFT and GRPO data for autoformalization yields up to 10.4pp semantic accuracy gains over full overlap, which renders the GRPO stage redundant.
Formarl: Enhancing autoformalization with no labeled data
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization
Disjoint SFT and GRPO data for autoformalization yields up to 10.4pp semantic accuracy gains over full overlap, which renders the GRPO stage redundant.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.