SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization
arXiv:2604.13515v1 Announce Type: cross
Abstract: Supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) is a common post-training recipe. We conduct a controlled ablation over SFT-GRPO data overlap, evaluating Qwen3-8B (th…