Language Model Crossover: Variation through Few-Shot Prompting

Elliot Meyerson & Mark J. Nelson & Herbie Bradley & Arash Moradi & Amy K. Hoover& Joel Lehman

Cognizant AI Labs | American University | University of Cambridge & CarperAI | New Jersey Institute of Technology |New Jersey Institute of Technology CarperAI


语言模型交叉：通过少数镜头提示的变化「本文为机器翻译+人工校对」

要点：

1.本文追求的是这样一种见解，即语言模型自然地使智能变异算子在精神上类似于进化交叉。特别是，具有足够规模的语言模型在上下文学习中发挥了作用，即它们可以从少量输入模式之间的关联中学习，以生成包含这种关联的输出（也称为少镜头提示）。

2.这种能力可以用来形成一个简单但强大的变异算子，即提示具有一些基于文本的基因型（如代码、纯文本句子或公式）的语言模型，并将其相应的输出解析为这些基因型的后代。这种语言模型交叉（实现简单，可以利用许多不同的开源语言模型）的前景是，它使一种简单的机制能够演化出语义丰富的文本表示（很少有特定领域的调整），并自然受益于当前语言模型的进步。

3.本文中的实验强调了语言模型交叉的多功能性，通过演化二进制位串、句子、公式、文本到图像提示和Python代码。结论是，语言模型交叉是一种很有前途的方法，可用于进化以文本表示的基因组。

一句话总结：
作为一种灵活且易于使用的遗传算子，LMX为EA从业者提供了一种利用最近大型神经模型革命的方法。这些实验解决了一系列潜在的应用，包括方程、纯文本句子、图像和代码，利用开源神经网络的广泛生态系统作为产生变异、交叉模态以及测量适应性和多样性的手段。

This paper pursues the insight that language models naturally enable an intelligent variation operator similar in spirit to evolutionary crossover. In particular, language models of sufficient scale demonstrate in-context learning, i.e. they can learn from associations between a small number of input patterns to generate outputs incorporating such associations (also called few-shot prompting). This ability can be leveraged to form a simple but powerful variation operator, i.e. to prompt a language model with a few text-based genotypes (such as code, plain-text sentences, or equations), and to parse its corresponding output as those genotypes’ offspring. The promise of such language model crossover (which is simple to implement and can leverage many different open-source language models) is that it enables a simple mechanism to evolve semantically-rich text representations (with few domain-specific tweaks), and naturally benefits from current progress in language models. Experiments in this paper highlight the versatility of language-model crossover,through evolving binary bit-strings, sentences, equations, text-to image prompts, and Python code. The conclusion is that language model crossover is a promising method for evolving genomes representable as text.

https://arxiv.org/pdf/2302.12170.pdf

内容中包含的图片若涉及版权问题，请及时与我们联系删除