A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design 事件

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design arXiv:2606.11189v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with the model prior. Strictly fitting toward this one-hot target may be suboptimal, especially when the pretrained model encodes a rich knowledge prior. In this work, we reinterpret SFT as target