Decoding the Black Box: Discerning AI Rhetorics About and Through Poetic Prompting

TL;DR

This paper explores how poetic prompts can reveal AI biases and tendencies, offering a new method for prompt engineering that enhances understanding of language model behaviors and their creative capacities.

Contribution

It introduces Poetry Prompt Patterns as a novel tool for analyzing and guiding large language models' responses and creative outputs.

Findings

Poetic prompts can uncover biases in language models.

Models show varying willingness to adapt or rewrite creative works.

Poetry prompts help assess model descriptions and evaluations.

Abstract

Prompt engineering has emerged as a useful way studying the algorithmic tendencies and biases of large language models. Meanwhile creatives and academics have leveraged LLMs to develop creative works and explore the boundaries of their writing capabilities through text generation and code. This study suggests that creative text prompting, specifically Poetry Prompt Patterns, may be a useful addition to the toolbox of the prompt engineer, and outlines the process by which this approach may be taken. Then, the paper uses poetic prompts to assess descriptions and evaluations of three models of a renowned poet and test the consequences of the willingness of models to adapt or rewrite original creative works for presumed audiences.