Skip to yearly menu bar Skip to main content


Poster

Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution

Chrisantha Fernando · Dylan Banarse · Henryk Michalewski · Simon Osindero · Tim Rocktäschel

Hall C 4-9 #611
[ ] [ Paper PDF ]
[ Poster
Thu 25 Jul 4:30 a.m. PDT — 6 a.m. PDT

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, evaluates them for fitness on a training set, and repeats this process over multiple generations to evolve task-prompts. 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 mutation-prompts 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.

Chat is not available.