Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
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.
Code (3)
Similar Papers 제목 키워드 기반
When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing
Large language models produce rich introspective language when prompted for self-examination, but whether this language reflects internal computation or sophisticated confabulation has remained unclear. We show that self…
Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work measures how consistent these reports are across repe…
When Self-Reference Fails to Close: Matrix-Level Dynamics in Large Language Models
We investigate how self-referential inputs alter the internal matrix dynamics of large language models. Measuring 106 scalar metrics across up to 7 analysis passes on four models from three architecture families -- Qwen3…
A Modern Self-Referential Weight Matrix That Learns to Modify Itself
The weight matrix (WM) of a neural network (NN) is its program. The programs of many traditional NNs are learned through gradient descent in some error function, then remain fixed. The WM of a self-referential NN, howeve…
Few-Shot LearningGödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or…
Mathematical ReasoningMeta-Learning