Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
This addresses the need for automated prompt optimization in LLMs, offering a novel approach that is not incremental but introduces a new paradigm for self-improvement.
The paper tackles the problem of sub-optimal hand-crafted prompt strategies for LLMs by introducing Promptbreeder, a self-referential mechanism that evolves prompts, resulting in outperforming state-of-the-art methods on arithmetic and commonsense reasoning benchmarks and evolving prompts for hate speech classification.
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.