Generative Verse: Large Language Models and the Future of Poetic Composition

Rezumat

This paper surveys the current landscape of poetry generation using large language models, examining both the technical capabilities and the aesthetic limitations of these systems. Through a series of experiments comparing LLM-generated verse with human-authored poetry across multiple dimensions (metaphor density, sonic patterning, emotional resonance), we investigate the boundaries of machine creativity and propose new evaluation frameworks for computational poetry.