1
Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
这篇论文颠覆了自我训练使语言扁平化的传统认知，揭示其本质是牺牲深层句法来放大表面标记的结构重构过程
arXiv:2605.20602v1 Announce Type: cross Abstract: Successive self-training on a language model's own outputs is widely characterized as a process of f…