不用改模型参数，把老师的能力写成文字教给学生
大模型之间的知识迁移，通常要动学生模型的参数——这等于把知识焊死在某个模型上，换个模型就得重来。这篇提出一个完全不同的路子：把老师模型和学生模型之间的差距，提炼成一份纯文字的「教案」，叫 Primer。流程像师徒制：学生做题，老师点评，助教把点评写成教学指令，再合成一份不断更新的文字教材。结果很猛：在代码生成任务上，学生准确率从 9.4% 提到 48.6%；数学推理从 27.6% 提到 51.7%。更关键的是，这份文字教案换一个学生模型也能用，不用重新训练。它不是你明天就能上手的产品，但它指向一个趋势：模型的能力也许能像书一样被写下来、传下去，而不是只能靠训练参数来继承。
📄 原文摘要(英文)
Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific architecture and checkpoint. This implicit representation is difficult to interpret or reuse across models and limits KD for API-only or costly-to-train models. This paper studies knowledge transfer for large language models (LLMs). We introduce Universal Textual Teaching (UTT), a parameter-update-free framework that distills observed Teacher-Student knowledge gaps into a textual, interpretable, and reusable natural-language artifact called Primer. Specifically, UTT first identifies representative gap cases through paired evaluations, and iteratively updates the Primer via multi-role interactions: the Student attempts each task, the Prompter turns evaluation feedback into a teaching instruction, the Teacher provides a targeted demonstration, and the Synthesizer consolidates validated lessons. Empirically, on the challenging math (Omni-MATH-2) and code generation (KernelBench) tasks, extensive results confirm the effectiveness of the method: UTT remarkably raises the Student's accuracy from 9.4% to 48.6% and Fast1 accuracy from 9% to 35% on KernelBench, while increasing mathematical reasoning accuracy from 27.6% to 51.7%. UTT also performs better than representative prompt engineering and parameter-based KD methods. Of note, UTT is shown to be generalizable across different Teachers and Students: a Primer synthesized for one Teacher-Student pair can generalize to other Students that do not participate in the synthesis.