Promptbreeder Selfreferential Selfimprovement Via Prompt Evolution

# Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

**arXiv ID:** 2309.16797
**Authors:** Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, Tim Rocktäschel
**Published:** 2023-09-28T19:01:07Z
**Abstract:**
Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-crafted prompt-strategies are often sub-optimal. In this paper, we present Promptbreeder, a general-purpose self-referential self-improvement mechanism that evolves and adapts prompts for a given domain. Driven by an LLM, Promptbreeder mutates a population of task-prompts, and subsequently evaluates them for fitness on a training set. Crucially, the mutation of these task-prompts is governed by mutation-prompts that the LLM generates and improves throughout evolution in a self-referential way. That is, Promptbreeder is not just improving task-prompts, but it is also improving the mutationprompts that improve these task-prompts. Promptbreeder outperforms state-of-the-art prompt strategies such as Chain-of-Thought and Plan-and-Solve Prompting on commonly used arithmetic and commonsense reasoning benchmarks. Furthermore, Promptbreeder is able to evolve intricate task-prompts for the challenging problem of hate speech classification.

## Skill Description

This skill is generated from the arXiv paper: Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (2309.16797).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2309.16797](http://arxiv.org/abs/2309.16797v1)