Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts 事件

Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts arXiv:2605.28042v1 Announce Type: new Abstract: Modern large language models (LLMs) achieve state-of-the-art machine translation performance, but they do so as broad generalists largely trained for many tasks and capabilities unrelated to translation. Thus, they are heavily overparameterized for this task, resulting in excessive memory and compute requirements. In this paper, we present a method for aggressively