shape-of-thought

【数据与研究】Demonstrate that synthetic CoT traces with incorrect final answers outperform human-written correct solutions for supervised fine-tuning. Distribution proximity between training data and student model's natural output matters more than correctness—validating human traces with model-like distributions improves performance, providing practical guidance…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准