1
TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
提出TANDEM双层优化框架,利用孪生网络自动搜索最优数据配比,为预训练数据混合提供新解法。
arXiv:2606.04401v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) significantly depend on training data drawn from vari…