Length Generalization Needs Proper Regularization

Length generalization is the ability of sequential models to perform well on context lengths unseen during training. In this work, we show that the challenge of achieving length generalization is related not only to architectural choices such as positional encoding and the attention mechanism but also to the training procedure itself. We study how regularization affects extrapolation of transformers and find that weight decay can hinder length generalization, while dropout improves the generalization when its placement within the architecture is reconsidered. In that regard, we show that the standard placement of dropout before layer normalization introduces a systematic distributional mismatch, and that applying dropout just before the linear projection resolves this issue. For example, a modified SmolLM3 with sliding window attention, continually pre-trained with dropout, can extrapolate perfectly to 64$\times$ on Needle-in-a-Haystack and far beyond the pre-training context size on RULER and HELMET. We further propose Variance-Preserving Affine Dropout (VPAD), a new dropout strategy that substantially reduces the resulting pre-activation variance mismatch, leading to further extrapolation improvements in transformers.