Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Abstract
Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization, called EvoPrompt, which borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence. To enable EAs to work on discrete prompts, which are natural language expressions that need to be coherent and human-readable, we connect LLMs with EAs. This approach allows us to simultaneously leverage the powerful language processing capabilities of LLMs and the efficient optimization performance of EAs. Specifically, abstaining from any gradients or parameters, EvoPrompt starts from a population of prompts and iteratively generates new prompts with LLMs based on the evolutionary operators, improving the population based on the development set. We optimize prompts for both closed- and open-source LLMs including GPT-3.5 and Alpaca, on 9 datasets spanning language understanding and generation tasks. EvoPrompt significantly outperforms human-engineered prompts and existing methods for automatic prompt generation by up to 25% and 14% respectively. Furthermore, EvoPrompt demonstrates that connecting LLMs with EAs creates synergies, which could inspire further research on the combination of LLMs and conventional algorithms.
Community
Friends, how can I test this technology?
Friends, how can I test this technology?
We will release the code soon. Thanks for your attention quotes.
Friends, how can I test this technology?
We will release the code soon. Thanks for your attention quotes.
Hello, is your code not yet released, or do you have an updated code release schedule?
Friends, how can I test this technology?
We will release the code soon. Thanks for your attention quotes.
Hello, is your code not yet released, or do you have an updated code release schedule?
Hi, we plan to release our code in 2 weeks.
is the code available now?
is the code available now?
The open-source of the code is on-going. We will share the link once it is available.
is the code available now?
Sorry for the late release of our open-source code. You may refer to this repo temporarily (https://github.com/beeevita/EvoPrompt) since the open-source of microsoft code is still in progress. If you find it helpful to your work, please star it. Thanks a lot~~😃😃
Friends, how can I test this technology?
We will release the code soon. Thanks for your attention quotes.
Hello, is your code not yet released, or do you have an updated code release schedule?
Sorry for the late release of our open-source code. You may refer to this repo temporarily (https://github.com/beeevita/EvoPrompt) since the open-source of microsoft code is still in progress. If you find it helpful to your work, please star it. Thanks a lot~~😃😃
Friends, how can I test this technology?
Sorry for the late release of our open-source code. You may refer to this repo temporarily (https://github.com/beeevita/EvoPrompt) since the open-source of microsoft code is still in progress. If you find it helpful to your work, please star it. Thanks a lot~~😃😃
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper