CritICL：用小模型错误提示提升大模型推理
Small models fail the same way big models do, so this paper shows you can collec…
Small models fail the same way big models do, so this paper shows you can collect a cheap model's mistakes once and use them to make a bigger model reason better.
小模型与大模型以相同方式出错，因此本文表明，你可以一次性收集廉价模型的错误，并利用它们让更大的模型推理得更好。
CritICL runs small models over math problems and saves every wrong answer with a short critique of what went wrong. When a new question arrives, the big model's prompt gets the critiques for the mistakes it is most likely to make.
CritICL在数学问题上运行小模型，并保存每个错误答案及简短批评说明出错原因。当新问题到来时，大模型的提示会包含它最可能犯的错误的批评。
That gets you the answer in 1 generation instead of 5.
这样只需一次生成即可得到答案，而非五次。
Building a bank of your model family's known failure modes once, then retrieving from it per query, appears to buy accuracy that usually costs repeated generations.
一次性构建你模型家族已知失败模式的库，然后按查询从中检索，似乎能买到通常需要多次生成才能获得的准确性。
This paper finds that a big model reasons better when its prompt warns it about the mistakes smaller models in its family keep making.
本文发现，当提示警告大模型其家族中较小模型常犯的错误时，大模型推理得更好。
Instead of running your model several times and voting, you may get the same accuracy by telling it upfront which mistakes it tends to make.
与其多次运行模型并投票，不如事先告诉它倾向于犯哪些错误，你或许能获得相同的准确性。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力